diff options
Diffstat (limited to 'thirdparty/icu4c/common/unicode')
48 files changed, 528 insertions, 329 deletions
diff --git a/thirdparty/icu4c/common/unicode/appendable.h b/thirdparty/icu4c/common/unicode/appendable.h index fc99254de1..f77df88e39 100644 --- a/thirdparty/icu4c/common/unicode/appendable.h +++ b/thirdparty/icu4c/common/unicode/appendable.h @@ -174,7 +174,7 @@ public: * @return true if the operation succeeded * @stable ICU 4.8 */ - virtual UBool appendCodeUnit(char16_t c); + virtual UBool appendCodeUnit(char16_t c) override; /** * Appends a code point to the string. @@ -182,7 +182,7 @@ public: * @return true if the operation succeeded * @stable ICU 4.8 */ - virtual UBool appendCodePoint(UChar32 c); + virtual UBool appendCodePoint(UChar32 c) override; /** * Appends a string to the UnicodeString. @@ -191,7 +191,7 @@ public: * @return true if the operation succeeded * @stable ICU 4.8 */ - virtual UBool appendString(const char16_t *s, int32_t length); + virtual UBool appendString(const char16_t *s, int32_t length) override; /** * Tells the UnicodeString that the caller is going to append roughly @@ -200,7 +200,7 @@ public: * @return true if the operation succeeded * @stable ICU 4.8 */ - virtual UBool reserveAppendCapacity(int32_t appendCapacity); + virtual UBool reserveAppendCapacity(int32_t appendCapacity) override; /** * Returns a writable buffer for appending and writes the buffer's capacity to @@ -226,7 +226,7 @@ public: virtual char16_t *getAppendBuffer(int32_t minCapacity, int32_t desiredCapacityHint, char16_t *scratch, int32_t scratchCapacity, - int32_t *resultCapacity); + int32_t *resultCapacity) override; private: UnicodeString &str; diff --git a/thirdparty/icu4c/common/unicode/brkiter.h b/thirdparty/icu4c/common/unicode/brkiter.h index 9bba5fcccc..3a121cf703 100644 --- a/thirdparty/icu4c/common/unicode/brkiter.h +++ b/thirdparty/icu4c/common/unicode/brkiter.h @@ -99,7 +99,7 @@ U_NAMESPACE_BEGIN * <p> * Code snippets illustrating the use of the Break Iterator APIs * are available in the ICU User Guide, - * http://icu-project.org/userguide/boundaryAnalysis.html + * https://unicode-org.github.io/icu/userguide/boundaryanalysis/ * and in the sample program icu/source/samples/break/break.cpp * */ @@ -124,7 +124,7 @@ public: * object, and styles are not considered. * @stable ICU 2.0 */ - virtual UBool operator==(const BreakIterator&) const = 0; + virtual bool operator==(const BreakIterator&) const = 0; /** * Returns the complement of the result of operator== @@ -132,7 +132,7 @@ public: * @return the complement of the result of operator== * @stable ICU 2.0 */ - UBool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); } + bool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); } /** * Return a polymorphic copy of this object. This is an abstract @@ -146,7 +146,7 @@ public: * will return distinct unequal values. * @stable ICU 2.0 */ - virtual UClassID getDynamicClassID(void) const = 0; + virtual UClassID getDynamicClassID(void) const override = 0; /** * Return a CharacterIterator over the text being analyzed. diff --git a/thirdparty/icu4c/common/unicode/bytestream.h b/thirdparty/icu4c/common/unicode/bytestream.h index 9735ee0bf8..997746e428 100644 --- a/thirdparty/icu4c/common/unicode/bytestream.h +++ b/thirdparty/icu4c/common/unicode/bytestream.h @@ -206,7 +206,7 @@ public: * @param n the number of bytes; must be non-negative * @stable ICU 4.2 */ - virtual void Append(const char* bytes, int32_t n); + virtual void Append(const char* bytes, int32_t n) override; /** * Returns a writable buffer for appending and writes the buffer's capacity to * *result_capacity. For details see the base class documentation. @@ -224,7 +224,7 @@ public: virtual char* GetAppendBuffer(int32_t min_capacity, int32_t desired_capacity_hint, char* scratch, int32_t scratch_capacity, - int32_t* result_capacity); + int32_t* result_capacity) override; /** * Returns the number of bytes actually written to the sink. * @return number of bytes written to the buffer @@ -291,7 +291,7 @@ class StringByteSink : public ByteSink { * @param n the number of bytes; must be non-negative * @stable ICU 4.2 */ - virtual void Append(const char* data, int32_t n) { dest_->append(data, n); } + virtual void Append(const char* data, int32_t n) override { dest_->append(data, n); } private: StringClass* dest_; diff --git a/thirdparty/icu4c/common/unicode/bytestriebuilder.h b/thirdparty/icu4c/common/unicode/bytestriebuilder.h index 3cff89e443..382f5e0095 100644 --- a/thirdparty/icu4c/common/unicode/bytestriebuilder.h +++ b/thirdparty/icu4c/common/unicode/bytestriebuilder.h @@ -134,21 +134,21 @@ private: void buildBytes(UStringTrieBuildOption buildOption, UErrorCode &errorCode); - virtual int32_t getElementStringLength(int32_t i) const; - virtual char16_t getElementUnit(int32_t i, int32_t byteIndex) const; - virtual int32_t getElementValue(int32_t i) const; + virtual int32_t getElementStringLength(int32_t i) const override; + virtual char16_t getElementUnit(int32_t i, int32_t byteIndex) const override; + virtual int32_t getElementValue(int32_t i) const override; - virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t byteIndex) const; + virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t byteIndex) const override; - virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t byteIndex) const; - virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t byteIndex, int32_t count) const; - virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t byteIndex, char16_t byte) const; + virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t byteIndex) const override; + virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t byteIndex, int32_t count) const override; + virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t byteIndex, char16_t byte) const override; - virtual UBool matchNodesCanHaveValues() const { return false; } + virtual UBool matchNodesCanHaveValues() const override { return false; } - virtual int32_t getMaxBranchLinearSubNodeLength() const { return BytesTrie::kMaxBranchLinearSubNodeLength; } - virtual int32_t getMinLinearMatch() const { return BytesTrie::kMinLinearMatch; } - virtual int32_t getMaxLinearMatchLength() const { return BytesTrie::kMaxLinearMatchLength; } + virtual int32_t getMaxBranchLinearSubNodeLength() const override { return BytesTrie::kMaxBranchLinearSubNodeLength; } + virtual int32_t getMinLinearMatch() const override { return BytesTrie::kMinLinearMatch; } + virtual int32_t getMaxLinearMatchLength() const override { return BytesTrie::kMaxLinearMatchLength; } /** * @internal (private) @@ -156,22 +156,22 @@ private: class BTLinearMatchNode : public LinearMatchNode { public: BTLinearMatchNode(const char *units, int32_t len, Node *nextNode); - virtual UBool operator==(const Node &other) const; - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual void write(StringTrieBuilder &builder) override; private: const char *s; }; virtual Node *createLinearMatchNode(int32_t i, int32_t byteIndex, int32_t length, - Node *nextNode) const; + Node *nextNode) const override; UBool ensureCapacity(int32_t length); - virtual int32_t write(int32_t byte); + virtual int32_t write(int32_t byte) override; int32_t write(const char *b, int32_t length); - virtual int32_t writeElementUnits(int32_t i, int32_t byteIndex, int32_t length); - virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal); - virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node); - virtual int32_t writeDeltaTo(int32_t jumpTarget); + virtual int32_t writeElementUnits(int32_t i, int32_t byteIndex, int32_t length) override; + virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal) override; + virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node) override; + virtual int32_t writeDeltaTo(int32_t jumpTarget) override; static int32_t internalEncodeDelta(int32_t i, char intBytes[]); CharString *strings; // Pointer not object so we need not #include internal charstr.h. diff --git a/thirdparty/icu4c/common/unicode/caniter.h b/thirdparty/icu4c/common/unicode/caniter.h index 4ed2b74b10..6e57ef5e3b 100644 --- a/thirdparty/icu4c/common/unicode/caniter.h +++ b/thirdparty/icu4c/common/unicode/caniter.h @@ -145,7 +145,7 @@ public: * * @stable ICU 2.2 */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; private: // ===================== PRIVATES ============================== @@ -194,7 +194,7 @@ private: /** * See if the decomposition of cp2 is at segment starting at segmentPos - * (with canonical rearrangment!) + * (with canonical rearrangement!) * If so, take the remainder, and return the equivalents */ //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer); diff --git a/thirdparty/icu4c/common/unicode/chariter.h b/thirdparty/icu4c/common/unicode/chariter.h index 96dc5db7c9..4f320b90e2 100644 --- a/thirdparty/icu4c/common/unicode/chariter.h +++ b/thirdparty/icu4c/common/unicode/chariter.h @@ -114,7 +114,7 @@ public: * character in the same character-storage object * @stable ICU 2.0 */ - virtual UBool operator==(const ForwardCharacterIterator& that) const = 0; + virtual bool operator==(const ForwardCharacterIterator& that) const = 0; /** * Returns true when the iterators refer to different @@ -126,7 +126,7 @@ public: * same text-storage object * @stable ICU 2.0 */ - inline UBool operator!=(const ForwardCharacterIterator& that) const; + inline bool operator!=(const ForwardCharacterIterator& that) const; /** * Generates a hash code for this iterator. @@ -142,7 +142,7 @@ public: * @return a UClassID for this ForwardCharacterIterator * @stable ICU 2.0 */ - virtual UClassID getDynamicClassID(void) const = 0; + virtual UClassID getDynamicClassID(void) const override = 0; /** * Gets the current code unit for returning and advances to the next code unit @@ -692,7 +692,7 @@ protected: int32_t end; }; -inline UBool +inline bool ForwardCharacterIterator::operator!=(const ForwardCharacterIterator& that) const { return !operator==(that); } diff --git a/thirdparty/icu4c/common/unicode/docmain.h b/thirdparty/icu4c/common/unicode/docmain.h index e82678c95f..4e29e283cd 100644 --- a/thirdparty/icu4c/common/unicode/docmain.h +++ b/thirdparty/icu4c/common/unicode/docmain.h @@ -47,7 +47,7 @@ * <h3>API References for Previous Releases</h3> * <p>The API References for each release of ICU are also available as * a zip file from the ICU - * <a href="http://site.icu-project.org/download">download page</a>.</p> + * <a href="https://icu.unicode.org/download">download page</a>.</p> * * <hr> * diff --git a/thirdparty/icu4c/common/unicode/dtintrv.h b/thirdparty/icu4c/common/unicode/dtintrv.h index 4f4b6bf7f4..46a94ce349 100644 --- a/thirdparty/icu4c/common/unicode/dtintrv.h +++ b/thirdparty/icu4c/common/unicode/dtintrv.h @@ -89,7 +89,7 @@ public: * other classes have different class IDs. * @stable ICU 4.0 */ - virtual UClassID getDynamicClassID(void) const; + virtual UClassID getDynamicClassID(void) const override; /** @@ -109,14 +109,14 @@ public: * @return true if the two DateIntervals are the same * @stable ICU 4.0 */ - virtual UBool operator==(const DateInterval& other) const; + virtual bool operator==(const DateInterval& other) const; /** * Non-equality operator * @return true if the two DateIntervals are not the same * @stable ICU 4.0 */ - inline UBool operator!=(const DateInterval& other) const; + inline bool operator!=(const DateInterval& other) const; /** @@ -151,7 +151,7 @@ DateInterval::getToDate() const { } -inline UBool +inline bool DateInterval::operator!=(const DateInterval& other) const { return ( !operator==(other) ); } diff --git a/thirdparty/icu4c/common/unicode/localebuilder.h b/thirdparty/icu4c/common/unicode/localebuilder.h index 27a894de10..f708a7ed7c 100644 --- a/thirdparty/icu4c/common/unicode/localebuilder.h +++ b/thirdparty/icu4c/common/unicode/localebuilder.h @@ -90,8 +90,7 @@ public: LocaleBuilder& setLocale(const Locale& locale); /** - * Resets the LocaleBuilder to match the provided - * [Unicode Locale Identifier](http://www.unicode.org/reports/tr35/tr35.html#unicode_locale_id) . + * Resets the LocaleBuilder to match the provided IETF BCP 47 language tag. * Discards the existing state. * The empty string causes the builder to be reset, like {@link #clear}. * Legacy language tags (marked as “Type: grandfathered” in BCP 47) @@ -101,8 +100,7 @@ public: * * <p>This method clears the internal UErrorCode. * - * @param tag the language tag, defined as - * [unicode_locale_id](http://www.unicode.org/reports/tr35/tr35.html#unicode_locale_id). + * @param tag the language tag, defined as IETF BCP 47 language tag. * @return This builder. * @stable ICU 64 */ diff --git a/thirdparty/icu4c/common/unicode/localematcher.h b/thirdparty/icu4c/common/unicode/localematcher.h index 0cd068ef32..252bb7fdc2 100644 --- a/thirdparty/icu4c/common/unicode/localematcher.h +++ b/thirdparty/icu4c/common/unicode/localematcher.h @@ -413,17 +413,15 @@ public: */ Builder &addSupportedLocale(const Locale &locale); -#ifndef U_HIDE_DRAFT_API /** * Sets no default locale. * There will be no explicit or implicit default locale. * If there is no good match, then the matcher will return nullptr for the * best supported locale. * - * @draft ICU 68 + * @stable ICU 68 */ Builder &setNoDefaultLocale(); -#endif // U_HIDE_DRAFT_API /** * Sets the default locale; if nullptr, or if it is not set explicitly, @@ -474,7 +472,6 @@ public: return *this; } -#ifndef U_HIDE_DRAFT_API /** * Sets the maximum distance for an acceptable match. * The matcher will return a match for a pair of locales only if @@ -494,10 +491,9 @@ public: * @param desired the desired locale for distance comparison. * @param supported the supported locale for distance comparison. * @return this Builder object - * @draft ICU 68 + * @stable ICU 68 */ Builder &setMaxDistance(const Locale &desired, const Locale &supported); -#endif // U_HIDE_DRAFT_API /** * Sets the UErrorCode if an error occurred while setting parameters. @@ -638,7 +634,6 @@ public: */ Result getBestMatchResult(Locale::Iterator &desiredLocales, UErrorCode &errorCode) const; -#ifndef U_HIDE_DRAFT_API /** * Returns true if the pair of locales matches acceptably. * This is influenced by Builder options such as setDirection(), setFavorSubtag(), @@ -650,10 +645,9 @@ public: * or else the function returns immediately. Check for U_FAILURE() * on output or use with function chaining. (See User Guide for details.) * @return true if the pair of locales matches acceptably. - * @draft ICU 68 + * @stable ICU 68 */ UBool isMatch(const Locale &desired, const Locale &supported, UErrorCode &errorCode) const; -#endif // U_HIDE_DRAFT_API #ifndef U_HIDE_INTERNAL_API /** diff --git a/thirdparty/icu4c/common/unicode/localpointer.h b/thirdparty/icu4c/common/unicode/localpointer.h index 2a65f2d382..96c659d10a 100644 --- a/thirdparty/icu4c/common/unicode/localpointer.h +++ b/thirdparty/icu4c/common/unicode/localpointer.h @@ -35,7 +35,7 @@ * - Need to be able to orphan/release the pointer and its ownership. * - Need variants for normal C++ object pointers, C++ arrays, and ICU C service objects. * - * For details see http://site.icu-project.org/design/cpp/scoped_ptr + * For details see https://icu.unicode.org/design/cpp/scoped_ptr */ #include "unicode/utypes.h" diff --git a/thirdparty/icu4c/common/unicode/locid.h b/thirdparty/icu4c/common/unicode/locid.h index 81f4685d65..2f2b3998a7 100644 --- a/thirdparty/icu4c/common/unicode/locid.h +++ b/thirdparty/icu4c/common/unicode/locid.h @@ -326,20 +326,20 @@ public: * Checks if two locale keys are the same. * * @param other The locale key object to be compared with this. - * @return True if the two locale keys are the same, false otherwise. + * @return true if the two locale keys are the same, false otherwise. * @stable ICU 2.0 */ - UBool operator==(const Locale& other) const; + bool operator==(const Locale& other) const; /** * Checks if two locale keys are not the same. * * @param other The locale key object to be compared with this. - * @return True if the two locale keys are not the same, false + * @return true if the two locale keys are not the same, false * otherwise. * @stable ICU 2.0 */ - inline UBool operator!=(const Locale& other) const; + inline bool operator!=(const Locale& other) const; /** * Clone this object. @@ -1005,7 +1005,7 @@ public: * * @stable ICU 2.2 */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; /** * A Locale iterator interface similar to a Java Iterator<Locale>. @@ -1163,7 +1163,7 @@ private: friend void U_CALLCONV locale_available_init(); }; -inline UBool +inline bool Locale::operator!=(const Locale& other) const { return !operator==(other); diff --git a/thirdparty/icu4c/common/unicode/messagepattern.h b/thirdparty/icu4c/common/unicode/messagepattern.h index 98e7b70b1f..4c5be13dbc 100644 --- a/thirdparty/icu4c/common/unicode/messagepattern.h +++ b/thirdparty/icu4c/common/unicode/messagepattern.h @@ -526,14 +526,14 @@ public: * @return true if this object is equivalent to the other one. * @stable ICU 4.8 */ - UBool operator==(const MessagePattern &other) const; + bool operator==(const MessagePattern &other) const; /** * @param other another object to compare with. * @return false if this object is equivalent to the other one. * @stable ICU 4.8 */ - inline UBool operator!=(const MessagePattern &other) const { + inline bool operator!=(const MessagePattern &other) const { return !operator==(other); } @@ -797,14 +797,14 @@ public: * @return true if this object is equivalent to the other one. * @stable ICU 4.8 */ - UBool operator==(const Part &other) const; + bool operator==(const Part &other) const; /** * @param other another object to compare with. * @return false if this object is equivalent to the other one. * @stable ICU 4.8 */ - inline UBool operator!=(const Part &other) const { + inline bool operator!=(const Part &other) const { return !operator==(other); } diff --git a/thirdparty/icu4c/common/unicode/normlzr.h b/thirdparty/icu4c/common/unicode/normlzr.h index 3352983cdc..93661990fe 100644 --- a/thirdparty/icu4c/common/unicode/normlzr.h +++ b/thirdparty/icu4c/common/unicode/normlzr.h @@ -584,7 +584,7 @@ public: * @return comparison result * @deprecated ICU 56 Use Normalizer2 instead. */ - UBool operator==(const Normalizer& that) const; + bool operator==(const Normalizer& that) const; /** * Returns false when both iterators refer to the same character in the same @@ -594,7 +594,7 @@ public: * @return comparison result * @deprecated ICU 56 Use Normalizer2 instead. */ - inline UBool operator!=(const Normalizer& that) const; + inline bool operator!=(const Normalizer& that) const; /** * Returns a pointer to a new Normalizer that is a clone of this one. @@ -732,7 +732,7 @@ public: * @return a UClassID for the actual class. * @deprecated ICU 56 Use Normalizer2 instead. */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; #endif // U_FORCE_HIDE_DEPRECATED_API private: @@ -777,7 +777,7 @@ private: //------------------------------------------------------------------------- #ifndef U_HIDE_DEPRECATED_API -inline UBool +inline bool Normalizer::operator!= (const Normalizer& other) const { return ! operator==(other); } diff --git a/thirdparty/icu4c/common/unicode/parsepos.h b/thirdparty/icu4c/common/unicode/parsepos.h index 260ed4cbb8..73945f5f97 100644 --- a/thirdparty/icu4c/common/unicode/parsepos.h +++ b/thirdparty/icu4c/common/unicode/parsepos.h @@ -100,14 +100,14 @@ public: * @return true if the two parse positions are equal, false otherwise. * @stable ICU 2.0 */ - inline UBool operator==(const ParsePosition& that) const; + inline bool operator==(const ParsePosition& that) const; /** * Equality operator. * @return true if the two parse positions are not equal, false otherwise. * @stable ICU 2.0 */ - inline UBool operator!=(const ParsePosition& that) const; + inline bool operator!=(const ParsePosition& that) const; /** * Clone this object. @@ -166,7 +166,7 @@ public: * * @stable ICU 2.2 */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; private: /** @@ -192,7 +192,7 @@ ParsePosition::operator=(const ParsePosition& copy) return *this; } -inline UBool +inline bool ParsePosition::operator==(const ParsePosition& copy) const { if(index != copy.index || errorIndex != copy.errorIndex) @@ -201,7 +201,7 @@ ParsePosition::operator==(const ParsePosition& copy) const return true; } -inline UBool +inline bool ParsePosition::operator!=(const ParsePosition& copy) const { return !operator==(copy); diff --git a/thirdparty/icu4c/common/unicode/platform.h b/thirdparty/icu4c/common/unicode/platform.h index cb3a833fef..b7e514442c 100644 --- a/thirdparty/icu4c/common/unicode/platform.h +++ b/thirdparty/icu4c/common/unicode/platform.h @@ -814,8 +814,8 @@ namespace std { /* Use the predefined value. */ #elif defined(U_STATIC_IMPLEMENTATION) # define U_EXPORT -#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(dllexport) && \ - UPRV_HAS_DECLSPEC_ATTRIBUTE(dllimport)) +#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(__dllexport__) && \ + UPRV_HAS_DECLSPEC_ATTRIBUTE(__dllimport__)) # define U_EXPORT __declspec(dllexport) #elif defined(__GNUC__) # define U_EXPORT __attribute__((visibility("default"))) @@ -839,8 +839,8 @@ namespace std { #ifdef U_IMPORT /* Use the predefined value. */ -#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(dllexport) && \ - UPRV_HAS_DECLSPEC_ATTRIBUTE(dllimport)) +#elif defined(_MSC_VER) || (UPRV_HAS_DECLSPEC_ATTRIBUTE(__dllexport__) && \ + UPRV_HAS_DECLSPEC_ATTRIBUTE(__dllimport__)) /* Windows needs to export/import data. */ # define U_IMPORT __declspec(dllimport) #else diff --git a/thirdparty/icu4c/common/unicode/rbbi.h b/thirdparty/icu4c/common/unicode/rbbi.h index 65117f616c..0ce93819f5 100644 --- a/thirdparty/icu4c/common/unicode/rbbi.h +++ b/thirdparty/icu4c/common/unicode/rbbi.h @@ -260,7 +260,7 @@ public: * same class, have the same behavior, and iterate over the same text. * @stable ICU 2.0 */ - virtual UBool operator==(const BreakIterator& that) const; + virtual bool operator==(const BreakIterator& that) const override; /** * Not-equal operator. If operator== returns true, this returns false, @@ -269,7 +269,7 @@ public: * @return true if both BreakIterators are not same. * @stable ICU 2.0 */ - inline UBool operator!=(const BreakIterator& that) const; + inline bool operator!=(const BreakIterator& that) const; /** * Returns a newly-constructed RuleBasedBreakIterator with the same @@ -281,7 +281,7 @@ public: * @return a newly-constructed RuleBasedBreakIterator * @stable ICU 2.0 */ - virtual RuleBasedBreakIterator* clone() const; + virtual RuleBasedBreakIterator* clone() const override; /** * Compute a hash code for this BreakIterator @@ -326,7 +326,7 @@ public: * @return An iterator over the text being analyzed. * @stable ICU 2.0 */ - virtual CharacterIterator& getText(void) const; + virtual CharacterIterator& getText(void) const override; /** @@ -343,7 +343,7 @@ public: * UText was provided, it will always be returned. * @stable ICU 3.4 */ - virtual UText *getUText(UText *fillIn, UErrorCode &status) const; + virtual UText *getUText(UText *fillIn, UErrorCode &status) const override; /** * Set the iterator to analyze a new piece of text. This function resets @@ -352,7 +352,7 @@ public: * takes ownership of the character iterator. The caller MUST NOT delete it! * @stable ICU 2.0 */ - virtual void adoptText(CharacterIterator* newText); + virtual void adoptText(CharacterIterator* newText) override; /** * Set the iterator to analyze a new piece of text. This function resets @@ -365,7 +365,7 @@ public: * @param newText The text to analyze. * @stable ICU 2.0 */ - virtual void setText(const UnicodeString& newText); + virtual void setText(const UnicodeString& newText) override; /** * Reset the break iterator to operate over the text represented by @@ -380,21 +380,21 @@ public: * @param status Receives any error codes. * @stable ICU 3.4 */ - virtual void setText(UText *text, UErrorCode &status); + virtual void setText(UText *text, UErrorCode &status) override; /** * Sets the current iteration position to the beginning of the text, position zero. * @return The offset of the beginning of the text, zero. * @stable ICU 2.0 */ - virtual int32_t first(void); + virtual int32_t first(void) override; /** * Sets the current iteration position to the end of the text. * @return The text's past-the-end offset. * @stable ICU 2.0 */ - virtual int32_t last(void); + virtual int32_t last(void) override; /** * Advances the iterator either forward or backward the specified number of steps. @@ -406,21 +406,21 @@ public: * the current one. * @stable ICU 2.0 */ - virtual int32_t next(int32_t n); + virtual int32_t next(int32_t n) override; /** * Advances the iterator to the next boundary position. * @return The position of the first boundary after this one. * @stable ICU 2.0 */ - virtual int32_t next(void); + virtual int32_t next(void) override; /** * Moves the iterator backwards, to the last boundary preceding this one. * @return The position of the last boundary position preceding this one. * @stable ICU 2.0 */ - virtual int32_t previous(void); + virtual int32_t previous(void) override; /** * Sets the iterator to refer to the first boundary position following @@ -429,7 +429,7 @@ public: * @return The position of the first break after the current position. * @stable ICU 2.0 */ - virtual int32_t following(int32_t offset); + virtual int32_t following(int32_t offset) override; /** * Sets the iterator to refer to the last boundary position before the @@ -438,7 +438,7 @@ public: * @return The position of the last boundary before the starting position. * @stable ICU 2.0 */ - virtual int32_t preceding(int32_t offset); + virtual int32_t preceding(int32_t offset) override; /** * Returns true if the specified position is a boundary position. As a side @@ -448,7 +448,7 @@ public: * @return True if "offset" is a boundary position. * @stable ICU 2.0 */ - virtual UBool isBoundary(int32_t offset); + virtual UBool isBoundary(int32_t offset) override; /** * Returns the current iteration position. Note that UBRK_DONE is never @@ -458,7 +458,7 @@ public: * @return The current iteration position. * @stable ICU 2.0 */ - virtual int32_t current(void) const; + virtual int32_t current(void) const override; /** @@ -492,7 +492,7 @@ public: * @see UWordBreak * @stable ICU 2.2 */ - virtual int32_t getRuleStatus() const; + virtual int32_t getRuleStatus() const override; /** * Get the status (tag) values from the break rule(s) that determined the boundary @@ -517,7 +517,7 @@ public: * @see getRuleStatus * @stable ICU 3.0 */ - virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status); + virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status) override; /** * Returns a unique class ID POLYMORPHICALLY. Pure virtual override. @@ -530,7 +530,7 @@ public: * other classes have different class IDs. * @stable ICU 2.0 */ - virtual UClassID getDynamicClassID(void) const; + virtual UClassID getDynamicClassID(void) const override; /** * Returns the class ID for this class. This is useful only for @@ -574,7 +574,7 @@ public: */ virtual RuleBasedBreakIterator *createBufferClone(void *stackBuffer, int32_t &BufferSize, - UErrorCode &status); + UErrorCode &status) override; #endif // U_FORCE_HIDE_DEPRECATED_API /** @@ -621,7 +621,7 @@ public: * * @stable ICU 49 */ - virtual RuleBasedBreakIterator &refreshInputText(UText *input, UErrorCode &status); + virtual RuleBasedBreakIterator &refreshInputText(UText *input, UErrorCode &status) override; private: @@ -719,7 +719,7 @@ private: // //------------------------------------------------------------------------------ -inline UBool RuleBasedBreakIterator::operator!=(const BreakIterator& that) const { +inline bool RuleBasedBreakIterator::operator!=(const BreakIterator& that) const { return !operator==(that); } diff --git a/thirdparty/icu4c/common/unicode/resbund.h b/thirdparty/icu4c/common/unicode/resbund.h index 37738e277b..7441592a0f 100644 --- a/thirdparty/icu4c/common/unicode/resbund.h +++ b/thirdparty/icu4c/common/unicode/resbund.h @@ -66,14 +66,14 @@ U_NAMESPACE_BEGIN /** * A class representing a collection of resource information pertaining to a given - * locale. A resource bundle provides a way of accessing locale- specfic information in + * locale. A resource bundle provides a way of accessing locale- specific information in * a data file. You create a resource bundle that manages the resources for a given * locale and then ask it for individual resources. * <P> * Resource bundles in ICU4C are currently defined using text files which conform to the following - * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/bnf_rb.txt">BNF definition</a>. + * <a href="https://github.com/unicode-org/icu-docs/blob/main/design/bnf_rb.txt">BNF definition</a>. * More on resource bundle concepts and syntax can be found in the - * <a href="http://icu-project.org/userguide/ResourceManagement.html">Users Guide</a>. + * <a href="https://unicode-org.github.io/icu/userguide/locale/resources">Users Guide</a>. * <P> * * The ResourceBundle class is not suitable for subclassing. @@ -474,7 +474,7 @@ public: * * @stable ICU 2.2 */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; /** * ICU "poor man's RTTI", returns a UClassID for this class. diff --git a/thirdparty/icu4c/common/unicode/schriter.h b/thirdparty/icu4c/common/unicode/schriter.h index 1ca5b70fca..9dac099967 100644 --- a/thirdparty/icu4c/common/unicode/schriter.h +++ b/thirdparty/icu4c/common/unicode/schriter.h @@ -124,7 +124,7 @@ public: * same string and are pointing at the same character. * @stable ICU 2.0 */ - virtual UBool operator==(const ForwardCharacterIterator& that) const; + virtual bool operator==(const ForwardCharacterIterator& that) const override; /** * Returns a new StringCharacterIterator referring to the same @@ -133,7 +133,7 @@ public: * @return the newly cloned object. * @stable ICU 2.0 */ - virtual StringCharacterIterator* clone() const; + virtual StringCharacterIterator* clone() const override; /** * Sets the iterator to iterate over the provided string. @@ -149,14 +149,14 @@ public: * @param result Receives a copy of the text under iteration. * @stable ICU 2.0 */ - virtual void getText(UnicodeString& result); + virtual void getText(UnicodeString& result) override; /** * Return a class ID for this object (not really public) * @return a class ID for this object. * @stable ICU 2.0 */ - virtual UClassID getDynamicClassID(void) const; + virtual UClassID getDynamicClassID(void) const override; /** * Return a class ID for this class (not really public) diff --git a/thirdparty/icu4c/common/unicode/strenum.h b/thirdparty/icu4c/common/unicode/strenum.h index df72b4b7e8..1d1b37940a 100644 --- a/thirdparty/icu4c/common/unicode/strenum.h +++ b/thirdparty/icu4c/common/unicode/strenum.h @@ -149,7 +149,7 @@ public: * and handles the conversion. * * @param status the error code. - * @param resultLength a ponter to receive the length, can be NULL. + * @param resultLength a pointer to receive the length, can be NULL. * @return a pointer to the string, or NULL. * * @stable ICU 2.4 @@ -199,7 +199,7 @@ public: * @return true if the enumerations are equal. false if not. * @stable ICU 3.6 */ - virtual UBool operator==(const StringEnumeration& that)const; + virtual bool operator==(const StringEnumeration& that)const; /** * Compares this enumeration to other to check if both are not equal * @@ -207,7 +207,7 @@ public: * @return true if the enumerations are equal. false if not. * @stable ICU 3.6 */ - virtual UBool operator!=(const StringEnumeration& that)const; + virtual bool operator!=(const StringEnumeration& that)const; protected: /** diff --git a/thirdparty/icu4c/common/unicode/stringpiece.h b/thirdparty/icu4c/common/unicode/stringpiece.h index 8c96789e73..df7f36089d 100644 --- a/thirdparty/icu4c/common/unicode/stringpiece.h +++ b/thirdparty/icu4c/common/unicode/stringpiece.h @@ -332,7 +332,7 @@ operator==(const StringPiece& x, const StringPiece& y); * @return true if the string data is not equal * @stable ICU 4.8 */ -inline UBool operator!=(const StringPiece& x, const StringPiece& y) { +inline bool operator!=(const StringPiece& x, const StringPiece& y) { return !(x == y); } diff --git a/thirdparty/icu4c/common/unicode/stringtriebuilder.h b/thirdparty/icu4c/common/unicode/stringtriebuilder.h index fe471bbbf9..b7a9b23d22 100644 --- a/thirdparty/icu4c/common/unicode/stringtriebuilder.h +++ b/thirdparty/icu4c/common/unicode/stringtriebuilder.h @@ -204,8 +204,8 @@ protected: // Handles node==NULL. static inline int32_t hashCode(const Node *node) { return node==NULL ? 0 : node->hashCode(); } // Base class operator==() compares the actual class types. - virtual UBool operator==(const Node &other) const; - inline UBool operator!=(const Node &other) const { return !operator==(other); } + virtual bool operator==(const Node &other) const; + inline bool operator!=(const Node &other) const { return !operator==(other); } /** * Traverses the Node graph and numbers branch edges, with rightmost edges first. * This is to avoid writing a duplicate node twice. @@ -265,8 +265,8 @@ protected: class FinalValueNode : public Node { public: FinalValueNode(int32_t v) : Node(0x111111u*37u+v), value(v) {} - virtual UBool operator==(const Node &other) const; - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual void write(StringTrieBuilder &builder) override; protected: int32_t value; }; @@ -280,7 +280,7 @@ protected: class ValueNode : public Node { public: ValueNode(int32_t initialHash) : Node(initialHash), hasValue(false), value(0) {} - virtual UBool operator==(const Node &other) const; + virtual bool operator==(const Node &other) const override; void setValue(int32_t v) { hasValue=true; value=v; @@ -299,9 +299,9 @@ protected: public: IntermediateValueNode(int32_t v, Node *nextNode) : ValueNode(0x222222u*37u+hashCode(nextNode)), next(nextNode) { setValue(v); } - virtual UBool operator==(const Node &other) const; - virtual int32_t markRightEdgesFirst(int32_t edgeNumber); - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber) override; + virtual void write(StringTrieBuilder &builder) override; protected: Node *next; }; @@ -317,8 +317,8 @@ protected: LinearMatchNode(int32_t len, Node *nextNode) : ValueNode((0x333333u*37u+len)*37u+hashCode(nextNode)), length(len), next(nextNode) {} - virtual UBool operator==(const Node &other) const; - virtual int32_t markRightEdgesFirst(int32_t edgeNumber); + virtual bool operator==(const Node &other) const override; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber) override; protected: int32_t length; Node *next; @@ -341,9 +341,9 @@ protected: class ListBranchNode : public BranchNode { public: ListBranchNode() : BranchNode(0x444444), length(0) {} - virtual UBool operator==(const Node &other) const; - virtual int32_t markRightEdgesFirst(int32_t edgeNumber); - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber) override; + virtual void write(StringTrieBuilder &builder) override; // Adds a unit with a final value. void add(int32_t c, int32_t value) { units[length]=(char16_t)c; @@ -376,9 +376,9 @@ protected: : BranchNode(((0x555555u*37u+middleUnit)*37u+ hashCode(lessThanNode))*37u+hashCode(greaterOrEqualNode)), unit(middleUnit), lessThan(lessThanNode), greaterOrEqual(greaterOrEqualNode) {} - virtual UBool operator==(const Node &other) const; - virtual int32_t markRightEdgesFirst(int32_t edgeNumber); - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber) override; + virtual void write(StringTrieBuilder &builder) override; protected: char16_t unit; Node *lessThan; @@ -392,9 +392,9 @@ protected: BranchHeadNode(int32_t len, Node *subNode) : ValueNode((0x666666u*37u+len)*37u+hashCode(subNode)), length(len), next(subNode) {} - virtual UBool operator==(const Node &other) const; - virtual int32_t markRightEdgesFirst(int32_t edgeNumber); - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual int32_t markRightEdgesFirst(int32_t edgeNumber) override; + virtual void write(StringTrieBuilder &builder) override; protected: int32_t length; Node *next; // A branch sub-node. diff --git a/thirdparty/icu4c/common/unicode/ubidi.h b/thirdparty/icu4c/common/unicode/ubidi.h index 63d0e45cb7..536f4172bc 100644 --- a/thirdparty/icu4c/common/unicode/ubidi.h +++ b/thirdparty/icu4c/common/unicode/ubidi.h @@ -84,7 +84,7 @@ * * <pre> * \code - *#include "unicode/ubidi.h" + *#include <unicode/ubidi.h> * *typedef enum { * styleNormal=0, styleSelected=1, @@ -136,11 +136,11 @@ * int styleLimit; * * for(i=0; i<styleRunCount; ++i) { - * styleLimit=styleRun[i].limit; + * styleLimit=styleRuns[i].limit; * if(start<styleLimit) { * if(styleLimit>limit) { styleLimit=limit; } * renderRun(text, start, styleLimit, - * direction, styleRun[i].style); + * direction, styleRuns[i].style); * if(styleLimit==limit) { break; } * start=styleLimit; * } @@ -150,14 +150,14 @@ * * for(i=styleRunCount-1; i>=0; --i) { * if(i>0) { - * styleStart=styleRun[i-1].limit; + * styleStart=styleRuns[i-1].limit; * } else { * styleStart=0; * } * if(limit>=styleStart) { * if(styleStart<start) { styleStart=start; } * renderRun(text, styleStart, limit, - * direction, styleRun[i].style); + * direction, styleRuns[i].style); * if(styleStart==start) { break; } * limit=styleStart; * } @@ -168,7 +168,8 @@ * // the line object represents text[start..limit-1] * void renderLine(UBiDi *line, const UChar *text, * int32_t start, int32_t limit, - * const StyleRun *styleRuns, int styleRunCount) { + * const StyleRun *styleRuns, int styleRunCount, + * UErrorCode *pErrorCode) { * UBiDiDirection direction=ubidi_getDirection(line); * if(direction!=UBIDI_MIXED) { * // unidirectional @@ -183,14 +184,14 @@ * int32_t count, i, length; * UBiDiLevel level; * - * count=ubidi_countRuns(para, pErrorCode); + * count=ubidi_countRuns(line, pErrorCode); * if(U_SUCCESS(*pErrorCode)) { * if(styleRunCount<=1) { * Style style=styleRuns[0].style; * * // iterate over directional runs * for(i=0; i<count; ++i) { - * direction=ubidi_getVisualRun(para, i, &start, &length); + * direction=ubidi_getVisualRun(line, i, &start, &length); * renderRun(text, start, start+length, direction, style); * } * } else { @@ -244,7 +245,7 @@ * startLine(paraLevel, width); * * renderLine(para, text, 0, length, - * styleRuns, styleRunCount); + * styleRuns, styleRunCount, pErrorCode); * } else { * UBiDi *line; * @@ -268,7 +269,7 @@ * * renderLine(line, text, start, limit, * styleRuns+styleRunStart, - * styleRunLimit-styleRunStart); + * styleRunLimit-styleRunStart, pErrorCode); * } * if(limit==length) { break; } * start=limit; diff --git a/thirdparty/icu4c/common/unicode/ubrk.h b/thirdparty/icu4c/common/unicode/ubrk.h index 1249b0b160..c603f7c13f 100644 --- a/thirdparty/icu4c/common/unicode/ubrk.h +++ b/thirdparty/icu4c/common/unicode/ubrk.h @@ -94,7 +94,7 @@ * <p> * Code snippets illustrating the use of the Break Iterator APIs * are available in the ICU User Guide, - * http://icu-project.org/userguide/boundaryAnalysis.html + * https://unicode-org.github.io/icu/userguide/boundaryanalysis/ * and in the sample program icu/source/samples/break/break.cpp */ diff --git a/thirdparty/icu4c/common/unicode/uchar.h b/thirdparty/icu4c/common/unicode/uchar.h index 1e0f82e706..253e6db173 100644 --- a/thirdparty/icu4c/common/unicode/uchar.h +++ b/thirdparty/icu4c/common/unicode/uchar.h @@ -60,7 +60,7 @@ U_CDECL_BEGIN * @see u_getUnicodeVersion * @stable ICU 2.0 */ -#define U_UNICODE_VERSION "13.0" +#define U_UNICODE_VERSION "14.0" /** * \file @@ -77,7 +77,7 @@ U_CDECL_BEGIN * * For more information see * "About the Unicode Character Database" (http://www.unicode.org/ucd/) - * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html). + * and the ICU User Guide chapter on Properties (https://unicode-org.github.io/icu/userguide/strings/properties). * * Many properties are accessible via generic functions that take a UProperty selector. * - u_hasBinaryProperty() returns a binary value (true/false) per property and code point. @@ -483,12 +483,63 @@ typedef enum UProperty { * @stable ICU 62 */ UCHAR_EXTENDED_PICTOGRAPHIC=64, +#ifndef U_HIDE_DRAFT_API + /** + * Binary property of strings Basic_Emoji. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_BASIC_EMOJI=65, + /** + * Binary property of strings Emoji_Keycap_Sequence. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_EMOJI_KEYCAP_SEQUENCE=66, + /** + * Binary property of strings RGI_Emoji_Modifier_Sequence. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_RGI_EMOJI_MODIFIER_SEQUENCE=67, + /** + * Binary property of strings RGI_Emoji_Flag_Sequence. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_RGI_EMOJI_FLAG_SEQUENCE=68, + /** + * Binary property of strings RGI_Emoji_Tag_Sequence. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_RGI_EMOJI_TAG_SEQUENCE=69, + /** + * Binary property of strings RGI_Emoji_ZWJ_Sequence. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_RGI_EMOJI_ZWJ_SEQUENCE=70, + /** + * Binary property of strings RGI_Emoji. + * See https://www.unicode.org/reports/tr51/#Emoji_Sets + * + * @draft ICU 70 + */ + UCHAR_RGI_EMOJI=71, +#endif // U_HIDE_DRAFT_API #ifndef U_HIDE_DEPRECATED_API /** * One more than the last constant for binary Unicode properties. * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. */ - UCHAR_BINARY_LIMIT, + UCHAR_BINARY_LIMIT=72, #endif // U_HIDE_DEPRECATED_API /** Enumerated property Bidi_Class. @@ -1807,6 +1858,33 @@ enum UBlockCode { /** @stable ICU 66 */ UBLOCK_YEZIDI = 308, /*[10E80]*/ + // New blocks in Unicode 14.0 + + /** @stable ICU 70 */ + UBLOCK_ARABIC_EXTENDED_B = 309, /*[0870]*/ + /** @stable ICU 70 */ + UBLOCK_CYPRO_MINOAN = 310, /*[12F90]*/ + /** @stable ICU 70 */ + UBLOCK_ETHIOPIC_EXTENDED_B = 311, /*[1E7E0]*/ + /** @stable ICU 70 */ + UBLOCK_KANA_EXTENDED_B = 312, /*[1AFF0]*/ + /** @stable ICU 70 */ + UBLOCK_LATIN_EXTENDED_F = 313, /*[10780]*/ + /** @stable ICU 70 */ + UBLOCK_LATIN_EXTENDED_G = 314, /*[1DF00]*/ + /** @stable ICU 70 */ + UBLOCK_OLD_UYGHUR = 315, /*[10F70]*/ + /** @stable ICU 70 */ + UBLOCK_TANGSA = 316, /*[16A70]*/ + /** @stable ICU 70 */ + UBLOCK_TOTO = 317, /*[1E290]*/ + /** @stable ICU 70 */ + UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED_A = 318, /*[11AB0]*/ + /** @stable ICU 70 */ + UBLOCK_VITHKUQI = 319, /*[10570]*/ + /** @stable ICU 70 */ + UBLOCK_ZNAMENNY_MUSICAL_NOTATION = 320, /*[1CF00]*/ + #ifndef U_HIDE_DEPRECATED_API /** * One more than the highest normal UBlockCode value. @@ -1814,7 +1892,7 @@ enum UBlockCode { * * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. */ - UBLOCK_COUNT = 309, + UBLOCK_COUNT = 321, #endif // U_HIDE_DEPRECATED_API /** @stable ICU 2.0 */ @@ -2106,6 +2184,9 @@ typedef enum UJoiningGroup { U_JG_HANIFI_ROHINGYA_KINNA_YA, /**< @stable ICU 62 */ U_JG_HANIFI_ROHINGYA_PA, /**< @stable ICU 62 */ + U_JG_THIN_YEH, /**< @stable ICU 70 */ + U_JG_VERTICAL_TAIL, /**< @stable ICU 70 */ + #ifndef U_HIDE_DEPRECATED_API /** * One more than the highest normal UJoiningGroup value. @@ -2585,10 +2666,10 @@ typedef enum UVerticalOrientation { * * @param c Code point to test. * @param which UProperty selector constant, identifies which binary property to check. - * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. * @return true or false according to the binary Unicode property value for c. * Also false if 'which' is out of bounds or if the Unicode version - * does not have data for the property at all, or not for this code point. + * does not have data for the property at all. * * @see UProperty * @see u_getBinaryPropertySet @@ -2599,6 +2680,37 @@ typedef enum UVerticalOrientation { U_CAPI UBool U_EXPORT2 u_hasBinaryProperty(UChar32 c, UProperty which); +#ifndef U_HIDE_DRAFT_API + +/** + * Returns true if the property is true for the string. + * Same as u_hasBinaryProperty(single code point, which) + * if the string contains exactly one code point. + * + * Most properties apply only to single code points. + * <a href="https://www.unicode.org/reports/tr51/#Emoji_Sets">UTS #51 Unicode Emoji</a> + * defines several properties of strings. + * + * @param s String to test. + * @param length Length of the string, or negative if NUL-terminated. + * @param which UProperty selector constant, identifies which binary property to check. + * Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT. + * @return true or false according to the binary Unicode property value for the string. + * Also false if 'which' is out of bounds or if the Unicode version + * does not have data for the property at all. + * + * @see UProperty + * @see u_hasBinaryProperty + * @see u_getBinaryPropertySet + * @see u_getIntPropertyValue + * @see u_getUnicodeVersion + * @draft ICU 70 + */ +U_CAPI UBool U_EXPORT2 +u_stringHasBinaryProperty(const UChar *s, int32_t length, UProperty which); + +#endif // U_HIDE_DRAFT_API + /** * Returns a frozen USet for a binary property. * The library retains ownership over the returned object. @@ -3834,7 +3946,7 @@ u_isJavaIDPart(UChar32 c); * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. * See also the User Guide chapter on C/POSIX migration: - * http://icu-project.org/userguide/posix.html#case_mappings + * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings * * @param c the code point to be mapped * @return the Simple_Lowercase_Mapping of the code point, if any; @@ -3859,7 +3971,7 @@ u_tolower(UChar32 c); * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. * See also the User Guide chapter on C/POSIX migration: - * http://icu-project.org/userguide/posix.html#case_mappings + * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings * * @param c the code point to be mapped * @return the Simple_Uppercase_Mapping of the code point, if any; @@ -3884,7 +3996,7 @@ u_toupper(UChar32 c); * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. * See also the User Guide chapter on C/POSIX migration: - * http://icu-project.org/userguide/posix.html#case_mappings + * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings * * @param c the code point to be mapped * @return the Simple_Titlecase_Mapping of the code point, if any; @@ -3908,7 +4020,7 @@ u_totitle(UChar32 c); * Full case mappings are applied by the string case mapping functions, * see ustring.h and the UnicodeString class. * See also the User Guide chapter on C/POSIX migration: - * http://icu-project.org/userguide/posix.html#case_mappings + * https://unicode-org.github.io/icu/userguide/icu/posix#case-mappings * * @param c the code point to be mapped * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I diff --git a/thirdparty/icu4c/common/unicode/ucharstriebuilder.h b/thirdparty/icu4c/common/unicode/ucharstriebuilder.h index 15657702f9..e0cb0acdc5 100644 --- a/thirdparty/icu4c/common/unicode/ucharstriebuilder.h +++ b/thirdparty/icu4c/common/unicode/ucharstriebuilder.h @@ -138,41 +138,41 @@ private: void buildUChars(UStringTrieBuildOption buildOption, UErrorCode &errorCode); - virtual int32_t getElementStringLength(int32_t i) const; - virtual char16_t getElementUnit(int32_t i, int32_t unitIndex) const; - virtual int32_t getElementValue(int32_t i) const; + virtual int32_t getElementStringLength(int32_t i) const override; + virtual char16_t getElementUnit(int32_t i, int32_t unitIndex) const override; + virtual int32_t getElementValue(int32_t i) const override; - virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t unitIndex) const; + virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t unitIndex) const override; - virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t unitIndex) const; - virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t unitIndex, int32_t count) const; - virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t unitIndex, char16_t unit) const; + virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t unitIndex) const override; + virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t unitIndex, int32_t count) const override; + virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t unitIndex, char16_t unit) const override; - virtual UBool matchNodesCanHaveValues() const { return true; } + virtual UBool matchNodesCanHaveValues() const override { return true; } - virtual int32_t getMaxBranchLinearSubNodeLength() const { return UCharsTrie::kMaxBranchLinearSubNodeLength; } - virtual int32_t getMinLinearMatch() const { return UCharsTrie::kMinLinearMatch; } - virtual int32_t getMaxLinearMatchLength() const { return UCharsTrie::kMaxLinearMatchLength; } + virtual int32_t getMaxBranchLinearSubNodeLength() const override { return UCharsTrie::kMaxBranchLinearSubNodeLength; } + virtual int32_t getMinLinearMatch() const override { return UCharsTrie::kMinLinearMatch; } + virtual int32_t getMaxLinearMatchLength() const override { return UCharsTrie::kMaxLinearMatchLength; } class UCTLinearMatchNode : public LinearMatchNode { public: UCTLinearMatchNode(const char16_t *units, int32_t len, Node *nextNode); - virtual UBool operator==(const Node &other) const; - virtual void write(StringTrieBuilder &builder); + virtual bool operator==(const Node &other) const override; + virtual void write(StringTrieBuilder &builder) override; private: const char16_t *s; }; virtual Node *createLinearMatchNode(int32_t i, int32_t unitIndex, int32_t length, - Node *nextNode) const; + Node *nextNode) const override; UBool ensureCapacity(int32_t length); - virtual int32_t write(int32_t unit); + virtual int32_t write(int32_t unit) override; int32_t write(const char16_t *s, int32_t length); - virtual int32_t writeElementUnits(int32_t i, int32_t unitIndex, int32_t length); - virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal); - virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node); - virtual int32_t writeDeltaTo(int32_t jumpTarget); + virtual int32_t writeElementUnits(int32_t i, int32_t unitIndex, int32_t length) override; + virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal) override; + virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node) override; + virtual int32_t writeDeltaTo(int32_t jumpTarget) override; UnicodeString strings; UCharsTrieElement *elements; diff --git a/thirdparty/icu4c/common/unicode/uchriter.h b/thirdparty/icu4c/common/unicode/uchriter.h index f5083561a8..9fae5e7de0 100644 --- a/thirdparty/icu4c/common/unicode/uchriter.h +++ b/thirdparty/icu4c/common/unicode/uchriter.h @@ -56,7 +56,7 @@ public: * The starting * position is specified by "position". If "position" is outside the valid * iteration range, the behavior of this object is undefined. - * @param textPtr The char16_t array to be iteratd over + * @param textPtr The char16_t array to be iterated over * @param length The length of the char16_t array * @param position The starting position of the iteration * @stable ICU 2.0 @@ -119,14 +119,14 @@ public: * same string and are pointing at the same character. * @stable ICU 2.0 */ - virtual UBool operator==(const ForwardCharacterIterator& that) const; + virtual bool operator==(const ForwardCharacterIterator& that) const override; /** * Generates a hash code for this iterator. * @return the hash code. * @stable ICU 2.0 */ - virtual int32_t hashCode(void) const; + virtual int32_t hashCode(void) const override; /** * Returns a new UCharCharacterIterator referring to the same @@ -135,7 +135,7 @@ public: * @return the CharacterIterator newly created * @stable ICU 2.0 */ - virtual UCharCharacterIterator* clone() const; + virtual UCharCharacterIterator* clone() const override; /** * Sets the iterator to refer to the first code unit in its @@ -144,7 +144,7 @@ public: * @return the first code unit in its iteration range. * @stable ICU 2.0 */ - virtual char16_t first(void); + virtual char16_t first(void) override; /** * Sets the iterator to refer to the first code unit in its @@ -154,7 +154,7 @@ public: * @return the first code unit in its iteration range * @stable ICU 2.0 */ - virtual char16_t firstPostInc(void); + virtual char16_t firstPostInc(void) override; /** * Sets the iterator to refer to the first code point in its @@ -165,7 +165,7 @@ public: * @return the first code point in its iteration range * @stable ICU 2.0 */ - virtual UChar32 first32(void); + virtual UChar32 first32(void) override; /** * Sets the iterator to refer to the first code point in its @@ -175,7 +175,7 @@ public: * @return the first code point in its iteration range. * @stable ICU 2.0 */ - virtual UChar32 first32PostInc(void); + virtual UChar32 first32PostInc(void) override; /** * Sets the iterator to refer to the last code unit in its @@ -184,7 +184,7 @@ public: * @return the last code unit in its iteration range. * @stable ICU 2.0 */ - virtual char16_t last(void); + virtual char16_t last(void) override; /** * Sets the iterator to refer to the last code point in its @@ -193,7 +193,7 @@ public: * @return the last code point in its iteration range. * @stable ICU 2.0 */ - virtual UChar32 last32(void); + virtual UChar32 last32(void) override; /** * Sets the iterator to refer to the "position"-th code unit @@ -203,7 +203,7 @@ public: * @return the code unit * @stable ICU 2.0 */ - virtual char16_t setIndex(int32_t position); + virtual char16_t setIndex(int32_t position) override; /** * Sets the iterator to refer to the beginning of the code point @@ -216,21 +216,21 @@ public: * @return the code unit * @stable ICU 2.0 */ - virtual UChar32 setIndex32(int32_t position); + virtual UChar32 setIndex32(int32_t position) override; /** * Returns the code unit the iterator currently refers to. * @return the code unit the iterator currently refers to. * @stable ICU 2.0 */ - virtual char16_t current(void) const; + virtual char16_t current(void) const override; /** * Returns the code point the iterator currently refers to. * @return the code point the iterator currently refers to. * @stable ICU 2.0 */ - virtual UChar32 current32(void) const; + virtual UChar32 current32(void) const override; /** * Advances to the next code unit in the iteration range (toward @@ -239,7 +239,7 @@ public: * @return the next code unit in the iteration range. * @stable ICU 2.0 */ - virtual char16_t next(void); + virtual char16_t next(void) override; /** * Gets the current code unit for returning and advances to the next code unit @@ -249,7 +249,7 @@ public: * @return the current code unit. * @stable ICU 2.0 */ - virtual char16_t nextPostInc(void); + virtual char16_t nextPostInc(void) override; /** * Advances to the next code point in the iteration range (toward @@ -261,7 +261,7 @@ public: * @return the next code point in the iteration range. * @stable ICU 2.0 */ - virtual UChar32 next32(void); + virtual UChar32 next32(void) override; /** * Gets the current code point for returning and advances to the next code point @@ -271,7 +271,7 @@ public: * @return the current point. * @stable ICU 2.0 */ - virtual UChar32 next32PostInc(void); + virtual UChar32 next32PostInc(void) override; /** * Returns false if there are no more code units or code points @@ -282,7 +282,7 @@ public: * at or after the current position in the iteration range. * @stable ICU 2.0 */ - virtual UBool hasNext(); + virtual UBool hasNext() override; /** * Advances to the previous code unit in the iteration range (toward @@ -291,7 +291,7 @@ public: * @return the previous code unit in the iteration range. * @stable ICU 2.0 */ - virtual char16_t previous(void); + virtual char16_t previous(void) override; /** * Advances to the previous code point in the iteration range (toward @@ -300,7 +300,7 @@ public: * @return the previous code point in the iteration range. * @stable ICU 2.0 */ - virtual UChar32 previous32(void); + virtual UChar32 previous32(void) override; /** * Returns false if there are no more code units or code points @@ -311,7 +311,7 @@ public: * before the current position in the iteration range. * @stable ICU 2.0 */ - virtual UBool hasPrevious(); + virtual UBool hasPrevious() override; /** * Moves the current position relative to the start or end of the @@ -324,7 +324,7 @@ public: * @return the new position * @stable ICU 2.0 */ - virtual int32_t move(int32_t delta, EOrigin origin); + virtual int32_t move(int32_t delta, EOrigin origin) override; /** * Moves the current position relative to the start or end of the @@ -341,7 +341,7 @@ public: // One of the system headers right now is sometimes defining a conflicting macro we don't use #undef move32 #endif - virtual int32_t move32(int32_t delta, EOrigin origin); + virtual int32_t move32(int32_t delta, EOrigin origin) override; /** * Sets the iterator to iterate over a new range of text @@ -356,7 +356,7 @@ public: * @param result Receives a copy of the text under iteration. * @stable ICU 2.0 */ - virtual void getText(UnicodeString& result); + virtual void getText(UnicodeString& result) override; /** * Return a class ID for this class (not really public) @@ -370,7 +370,7 @@ public: * @return a class ID for this object. * @stable ICU 2.0 */ - virtual UClassID getDynamicClassID(void) const; + virtual UClassID getDynamicClassID(void) const override; protected: /** diff --git a/thirdparty/icu4c/common/unicode/ucnv.h b/thirdparty/icu4c/common/unicode/ucnv.h index 5d784990f2..2687c984d4 100644 --- a/thirdparty/icu4c/common/unicode/ucnv.h +++ b/thirdparty/icu4c/common/unicode/ucnv.h @@ -42,8 +42,7 @@ * many other callback actions that can be used instead of a character substitution.</p> * * <p>More information about this API can be found in our - * <a href="http://icu-project.org/userguide/conversion.html">User's - * Guide</a>.</p> + * <a href="https://unicode-org.github.io/icu/userguide/conversion/">User Guide</a>.</p> */ #ifndef UCNV_H @@ -340,7 +339,7 @@ ucnv_compareNames(const char *name1, const char *name2); * * <p>The conversion behavior and names can vary between platforms. ICU may * convert some characters differently from other platforms. Details on this topic - * are in the <a href="http://icu-project.org/userguide/conversion.html">User's + * are in the <a href="https://unicode-org.github.io/icu/userguide/conversion/">User * Guide</a>. Aliases starting with a "cp" prefix have no specific meaning * other than its an alias starting with the letters "cp". Please do not * associate any meaning to these aliases.</p> @@ -1007,7 +1006,7 @@ ucnv_getUnicodeSet(const UConverter *cnv, UErrorCode *pErrorCode); /** - * Gets the current calback function used by the converter when an illegal + * Gets the current callback function used by the converter when an illegal * or invalid codepage sequence is found. * Context pointers are always owned by the caller. * @@ -1935,7 +1934,7 @@ ucnv_isAmbiguous(const UConverter *cnv); * reverse fallbacks (to Unicode). * For details see ".ucm File Format" * in the Conversion Data chapter of the ICU User Guide: - * http://www.icu-project.org/userguide/conversion-data.html#ucmformat + * https://unicode-org.github.io/icu/userguide/conversion/data.html#ucm-file-format * * @param cnv The converter to set the fallback mapping usage on. * @param usesFallback true if the user wants the converter to take advantage of the fallback @@ -2032,7 +2031,7 @@ ucnv_toUCountPending(const UConverter* cnv, UErrorCode* status); * fixed ratio of bytes to Unicode codes <i>units</i> for any particular Unicode encoding form. * false is returned with the UErrorCode if error occurs or cnv is NULL. * @param cnv The converter to be tested - * @param status ICU error code in/out paramter + * @param status ICU error code in/out parameter * @return true if the converter is fixed-width * @stable ICU 4.8 */ diff --git a/thirdparty/icu4c/common/unicode/ucnv_err.h b/thirdparty/icu4c/common/unicode/ucnv_err.h index 7209ba5f7b..a13d01db09 100644 --- a/thirdparty/icu4c/common/unicode/ucnv_err.h +++ b/thirdparty/icu4c/common/unicode/ucnv_err.h @@ -268,7 +268,7 @@ U_CAPI void U_EXPORT2 UCNV_TO_U_CALLBACK_STOP ( /** * DO NOT CALL THIS FUNCTION DIRECTLY! * This From Unicode callback skips any ILLEGAL_SEQUENCE, or - * skips only UNASSINGED_SEQUENCE depending on the context parameter + * skips only UNASSIGNED_SEQUENCE depending on the context parameter * simply ignoring those characters. * * @param context The function currently recognizes the callback options: @@ -330,31 +330,31 @@ U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_SUBSTITUTE ( * * @param context The function currently recognizes the callback options: * <ul> - * <li>UCNV_ESCAPE_ICU: Substitues the ILLEGAL SEQUENCE with the hexadecimal + * <li>UCNV_ESCAPE_ICU: Substitutes the ILLEGAL SEQUENCE with the hexadecimal * representation in the format %UXXXX, e.g. "%uFFFE%u00AC%uC8FE"). * In the Event the converter doesn't support the characters {%,U}[A-F][0-9], * it will substitute the illegal sequence with the substitution characters. * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as * %UD84D%UDC56</li> - * <li>UCNV_ESCAPE_JAVA: Substitues the ILLEGAL SEQUENCE with the hexadecimal + * <li>UCNV_ESCAPE_JAVA: Substitutes the ILLEGAL SEQUENCE with the hexadecimal * representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE"). * In the Event the converter doesn't support the characters {\,u}[A-F][0-9], * it will substitute the illegal sequence with the substitution characters. * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as * \\uD84D\\uDC56</li> - * <li>UCNV_ESCAPE_C: Substitues the ILLEGAL SEQUENCE with the hexadecimal + * <li>UCNV_ESCAPE_C: Substitutes the ILLEGAL SEQUENCE with the hexadecimal * representation in the format \\uXXXX, e.g. "\\uFFFE\\u00AC\\uC8FE"). * In the Event the converter doesn't support the characters {\,u,U}[A-F][0-9], * it will substitute the illegal sequence with the substitution characters. * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as * \\U00023456</li> - * <li>UCNV_ESCAPE_XML_DEC: Substitues the ILLEGAL SEQUENCE with the decimal + * <li>UCNV_ESCAPE_XML_DEC: Substitutes the ILLEGAL SEQUENCE with the decimal * representation in the format \htmlonly&#DDDDDDDD;, e.g. "&#65534;&#172;&#51454;")\endhtmlonly. * In the Event the converter doesn't support the characters {&,#}[0-9], * it will substitute the illegal sequence with the substitution characters. * Note that codeUnit(32bit int eg: unit of a surrogate pair) is represented as * &#144470; and Zero padding is ignored.</li> - * <li>UCNV_ESCAPE_XML_HEX:Substitues the ILLEGAL SEQUENCE with the decimal + * <li>UCNV_ESCAPE_XML_HEX:Substitutes the ILLEGAL SEQUENCE with the decimal * representation in the format \htmlonly&#xXXXX; e.g. "&#xFFFE;&#x00AC;&#xC8FE;")\endhtmlonly. * In the Event the converter doesn't support the characters {&,#,x}[0-9], * it will substitute the illegal sequence with the substitution characters. @@ -383,7 +383,7 @@ U_CAPI void U_EXPORT2 UCNV_FROM_U_CALLBACK_ESCAPE ( /** * DO NOT CALL THIS FUNCTION DIRECTLY! * This To Unicode callback skips any ILLEGAL_SEQUENCE, or - * skips only UNASSINGED_SEQUENCE depending on the context parameter + * skips only UNASSIGNED_SEQUENCE depending on the context parameter * simply ignoring those characters. * * @param context The function currently recognizes the callback options: diff --git a/thirdparty/icu4c/common/unicode/ucptrie.h b/thirdparty/icu4c/common/unicode/ucptrie.h index b95491b183..e2547ae2ee 100644 --- a/thirdparty/icu4c/common/unicode/ucptrie.h +++ b/thirdparty/icu4c/common/unicode/ucptrie.h @@ -43,7 +43,7 @@ typedef union UCPTrieData { /** * Immutable Unicode code point trie structure. * Fast, reasonably compact, map from Unicode code points (U+0000..U+10FFFF) to integer values. - * For details see http://site.icu-project.org/design/struct/utrie + * For details see https://icu.unicode.org/design/struct/utrie * * Do not access UCPTrie fields directly; use public functions and macros. * Functions are easy to use: They support all trie types and value widths. diff --git a/thirdparty/icu4c/common/unicode/ucurr.h b/thirdparty/icu4c/common/unicode/ucurr.h index 35c2a39389..5589e79990 100644 --- a/thirdparty/icu4c/common/unicode/ucurr.h +++ b/thirdparty/icu4c/common/unicode/ucurr.h @@ -115,14 +115,13 @@ typedef enum UCurrNameStyle { */ UCURR_NARROW_SYMBOL_NAME, -#ifndef U_HIDE_DRAFT_API /** * Selector for getName() indicating the formal currency symbol. * The formal currency symbol is similar to the regular currency * symbol, but it always takes the form used in formal settings * such as banking; for example, "NT$" instead of "$" for TWD in zh-TW. * - * @draft ICU 68 + * @stable ICU 68 */ UCURR_FORMAL_SYMBOL_NAME, @@ -131,10 +130,9 @@ typedef enum UCurrNameStyle { * The variant symbol for a currency is an alternative symbol * that is not necessarily as widely used as the regular symbol. * - * @draft ICU 68 + * @stable ICU 68 */ UCURR_VARIANT_SYMBOL_NAME -#endif // U_HIDE_DRAFT_API } UCurrNameStyle; diff --git a/thirdparty/icu4c/common/unicode/udata.h b/thirdparty/icu4c/common/unicode/udata.h index 6caa849c42..c5b1adc359 100644 --- a/thirdparty/icu4c/common/unicode/udata.h +++ b/thirdparty/icu4c/common/unicode/udata.h @@ -231,7 +231,7 @@ udata_open(const char *path, const char *type, const char *name, * logically prepended to the ICU data directory string.</p> * * <p>For details about ICU data loading see the User Guide - * Data Management chapter. (http://icu-project.org/userguide/icudata.html)</p> + * Data Management chapter. (https://unicode-org.github.io/icu/userguide/icu_data/)</p> * * @param path Specifies an absolute path and/or a basename for the * finding of the data in the file system. @@ -362,7 +362,7 @@ udata_setCommonData(const void *data, UErrorCode *err); * * * Warning: setAppData will set a U_USING_DEFAULT_WARNING code if - * data with the specifed path that has already been opened, or + * data with the specified path that has already been opened, or * if setAppData with the same path has already been called. * Any such calls to setAppData will have no effect. * diff --git a/thirdparty/icu4c/common/unicode/uloc.h b/thirdparty/icu4c/common/unicode/uloc.h index 3addb847e7..b0bdbe1b87 100644 --- a/thirdparty/icu4c/common/unicode/uloc.h +++ b/thirdparty/icu4c/common/unicode/uloc.h @@ -841,7 +841,7 @@ typedef enum ULocAvailableType { * @internal */ ULOC_AVAILABLE_COUNT -#endif +#endif /* U_HIDE_INTERNAL_API */ } ULocAvailableType; /** diff --git a/thirdparty/icu4c/common/unicode/umutablecptrie.h b/thirdparty/icu4c/common/unicode/umutablecptrie.h index 5325d58147..3b950055da 100644 --- a/thirdparty/icu4c/common/unicode/umutablecptrie.h +++ b/thirdparty/icu4c/common/unicode/umutablecptrie.h @@ -31,7 +31,7 @@ U_CDECL_BEGIN /** * Mutable Unicode code point trie. * Fast map from Unicode code points (U+0000..U+10FFFF) to 32-bit integer values. - * For details see http://site.icu-project.org/design/struct/utrie + * For details see https://icu.unicode.org/design/struct/utrie * * Setting values (especially ranges) and lookup is fast. * The mutable trie is only somewhat space-efficient. diff --git a/thirdparty/icu4c/common/unicode/unifilt.h b/thirdparty/icu4c/common/unicode/unifilt.h index 7870b55939..0fcaf4b789 100644 --- a/thirdparty/icu4c/common/unicode/unifilt.h +++ b/thirdparty/icu4c/common/unicode/unifilt.h @@ -77,7 +77,7 @@ public: * @return clone, or nullptr if an error occurred * @stable ICU 2.4 */ - virtual UnicodeFilter* clone() const = 0; + virtual UnicodeFilter* clone() const override = 0; /** * Returns <tt>true</tt> for characters that are in the selected @@ -93,7 +93,7 @@ public: * and return the pointer. * @stable ICU 2.4 */ - virtual UnicodeMatcher* toMatcher() const; + virtual UnicodeMatcher* toMatcher() const override; /** * Implement UnicodeMatcher API. @@ -102,13 +102,13 @@ public: virtual UMatchDegree matches(const Replaceable& text, int32_t& offset, int32_t limit, - UBool incremental); + UBool incremental) override; /** * UnicodeFunctor API. Nothing to do. * @stable ICU 2.4 */ - virtual void setData(const TransliterationRuleData*); + virtual void setData(const TransliterationRuleData*) override; /** * ICU "poor man's RTTI", returns a UClassID for this class. diff --git a/thirdparty/icu4c/common/unicode/unifunct.h b/thirdparty/icu4c/common/unicode/unifunct.h index 7d31af7daf..8751302494 100644 --- a/thirdparty/icu4c/common/unicode/unifunct.h +++ b/thirdparty/icu4c/common/unicode/unifunct.h @@ -93,14 +93,14 @@ public: * * <p>Concrete subclasses of UnicodeFunctor should use the macro * UOBJECT_DEFINE_RTTI_IMPLEMENTATION from uobject.h to - * provide definitios getStaticClassID and getDynamicClassID. + * provide definitions getStaticClassID and getDynamicClassID. * * @return The class ID for this object. All objects of a given * class have the same class ID. Objects of other classes have * different class IDs. * @stable ICU 2.4 */ - virtual UClassID getDynamicClassID(void) const = 0; + virtual UClassID getDynamicClassID(void) const override = 0; /** * Set the data object associated with this functor. The data diff --git a/thirdparty/icu4c/common/unicode/uniset.h b/thirdparty/icu4c/common/unicode/uniset.h index 8403c4026c..730337a353 100644 --- a/thirdparty/icu4c/common/unicode/uniset.h +++ b/thirdparty/icu4c/common/unicode/uniset.h @@ -124,8 +124,8 @@ class RuleCharacterIterator; * "[:Lu:]" and the Perl-like syntax "\\p{Lu}" are recognized. For a * complete list of supported property patterns, see the User's Guide * for UnicodeSet at - * <a href="http://icu-project.org/userguide/unicodeSet.html"> - * http://icu-project.org/userguide/unicodeSet.html</a>. + * <a href="https://unicode-org.github.io/icu/userguide/strings/unicodeset"> + * https://unicode-org.github.io/icu/userguide/strings/unicodeset</a>. * Actual determination of property data is defined by the underlying * Unicode database as implemented by UCharacter. * @@ -136,6 +136,13 @@ class RuleCharacterIterator; * their delimiters; "[:^foo]" and "\\P{foo}". In any other location, * '^' has no special meaning. * + * <p>Since ICU 70, "[^...]", "[:^foo]", "\\P{foo}", and "[:binaryProperty=No:]" + * perform a “code point complement” (all code points minus the original set), + * removing all multicharacter strings, + * equivalent to <code>.complement().removeAllStrings()</code>. + * The complement() API function continues to perform a + * symmetric difference with all code points and thus retains all multicharacter strings. + * * <p>Ranges are indicated by placing two a '-' between two * characters, as in "a-z". This specifies the range of all * characters from the left to the right, in Unicode order. If the @@ -217,9 +224,8 @@ class RuleCharacterIterator; * </tr> * <tr align="top"> * <td nowrap valign="top" align="right"><code>hex := </code></td> - * <td valign="top"><em>any character for which - * </em><code>Character.digit(c, 16)</code><em> - * returns a non-negative result</em></td> + * <td valign="top"><code>'0' | '1' | '2' | '3' | '4' | '5' | '6' | '7' | '8' | '9' |<br> + * 'A' | 'B' | 'C' | 'D' | 'E' | 'F' | 'a' | 'b' | 'c' | 'd' | 'e' | 'f'</code></td> * </tr> * <tr> * <td nowrap valign="top" align="right"><code>property := </code></td> @@ -485,14 +491,14 @@ public: * @return <tt>true</tt> if the specified set is equal to this set. * @stable ICU 2.0 */ - virtual UBool operator==(const UnicodeSet& o) const; + virtual bool operator==(const UnicodeSet& o) const; /** * Compares the specified object with this set for equality. Returns * <tt>true</tt> if the specified set is not equal to this set. * @stable ICU 2.0 */ - inline UBool operator!=(const UnicodeSet& o) const; + inline bool operator!=(const UnicodeSet& o) const; /** * Returns a copy of this object. All UnicodeFunctor objects have @@ -503,7 +509,7 @@ public: * @see cloneAsThawed * @stable ICU 2.0 */ - virtual UnicodeSet* clone() const; + virtual UnicodeSet* clone() const override; /** * Returns the hash code value for this set. @@ -705,7 +711,7 @@ public: * @stable ICU 2.0 */ virtual UnicodeString& toPattern(UnicodeString& result, - UBool escapeUnprintable = false) const; + UBool escapeUnprintable = false) const override; /** * Modifies this set to contain those code points which have the given value @@ -771,8 +777,12 @@ public: * Note than the elements of a set may include both individual * codepoints and strings. * + * This is slower than getRangeCount() because + * it counts the code points of all ranges. + * * @return the number of elements in this set (its cardinality). * @stable ICU 2.0 + * @see getRangeCount */ virtual int32_t size(void) const; @@ -784,6 +794,14 @@ public: */ virtual UBool isEmpty(void) const; +#ifndef U_HIDE_DRAFT_API + /** + * @return true if this set contains multi-character strings or the empty string. + * @draft ICU 70 + */ + UBool hasStrings() const; +#endif // U_HIDE_DRAFT_API + /** * Returns true if this set contains the given character. * This function works faster with a frozen set. @@ -791,7 +809,7 @@ public: * @return true if the test condition is met * @stable ICU 2.0 */ - virtual UBool contains(UChar32 c) const; + virtual UBool contains(UChar32 c) const override; /** * Returns true if this set contains every character @@ -1000,7 +1018,7 @@ public: virtual UMatchDegree matches(const Replaceable& text, int32_t& offset, int32_t limit, - UBool incremental); + UBool incremental) override; private: /** @@ -1049,7 +1067,7 @@ public: * @param toUnionTo the set into which to union the source characters * @stable ICU 2.4 */ - virtual void addMatchSetTo(UnicodeSet& toUnionTo) const; + virtual void addMatchSetTo(UnicodeSet& toUnionTo) const override; /** * Returns the index of the given character within this set, where @@ -1064,8 +1082,14 @@ public: /** * Returns the character at the given index within this set, where * the set is ordered by ascending code point. If the index is - * out of range, return (UChar32)-1. The inverse of this method is - * <code>indexOf()</code>. + * out of range for characters, returns (UChar32)-1. + * The inverse of this method is <code>indexOf()</code>. + * + * For iteration, this is slower than UnicodeSetIterator or + * getRangeCount()/getRangeStart()/getRangeEnd(), + * because for each call it skips linearly over <code>index</code> + * characters in the ranges. + * * @param index an index from 0..size()-1 * @return the character at the given index, or (UChar32)-1. * @stable ICU 2.4 @@ -1258,13 +1282,18 @@ public: UnicodeSet& remove(const UnicodeString& s); /** - * Inverts this set. This operation modifies this set so that - * its value is its complement. This is equivalent to + * This is equivalent to * <code>complement(MIN_VALUE, MAX_VALUE)</code>. + * + * <strong>Note:</strong> This performs a symmetric difference with all code points + * <em>and thus retains all multicharacter strings</em>. + * In order to achieve a “code point complement” (all code points minus this set), + * the easiest is to <code>.complement().removeAllStrings()</code>. + * * A frozen set will not be modified. * @stable ICU 2.0 */ - virtual UnicodeSet& complement(void); + virtual UnicodeSet& complement(); /** * Complements the specified range in this set. Any character in @@ -1504,7 +1533,7 @@ public: * different class IDs. * @stable ICU 2.4 */ - virtual UClassID getDynamicClassID(void) const; + virtual UClassID getDynamicClassID(void) const override; private: @@ -1525,7 +1554,7 @@ private: * is the given value. This is used by <tt>RuleBasedTransliterator</tt> for * indexing. */ - virtual UBool matchesIndexValue(uint8_t v) const; + virtual UBool matchesIndexValue(uint8_t v) const override; private: friend class RBBIRuleScanner; @@ -1567,7 +1596,6 @@ private: void swapBuffers(void); UBool allocateStrings(UErrorCode &status); - UBool hasStrings() const; int32_t stringsSize() const; UBool stringsContains(const UnicodeString &s) const; @@ -1581,6 +1609,9 @@ private: static void _appendToPat(UnicodeString& buf, UChar32 c, UBool escapeUnprintable); + static void _appendToPat(UnicodeString &result, UChar32 start, UChar32 end, + UBool escapeUnprintable); + //---------------------------------------------------------------- // Implementation: Fundamental operators //---------------------------------------------------------------- @@ -1608,7 +1639,7 @@ private: * * The original design document is out of date, but still useful. * Ignore the property and value names: - * http://source.icu-project.org/repos/icu/icuhtml/trunk/design/unicodeset_properties.html + * https://htmlpreview.github.io/?https://github.com/unicode-org/icu-docs/blob/main/design/unicodeset_properties.html * * Recognized syntax: * @@ -1693,7 +1724,7 @@ private: -inline UBool UnicodeSet::operator!=(const UnicodeSet& o) const { +inline bool UnicodeSet::operator!=(const UnicodeSet& o) const { return !operator==(o); } diff --git a/thirdparty/icu4c/common/unicode/unistr.h b/thirdparty/icu4c/common/unicode/unistr.h index 85bd964951..b3c9948107 100644 --- a/thirdparty/icu4c/common/unicode/unistr.h +++ b/thirdparty/icu4c/common/unicode/unistr.h @@ -325,7 +325,7 @@ public: * false otherwise. * @stable ICU 2.0 */ - inline UBool operator== (const UnicodeString& text) const; + inline bool operator== (const UnicodeString& text) const; /** * Inequality operator. Performs only bitwise comparison. @@ -334,7 +334,7 @@ public: * true otherwise. * @stable ICU 2.0 */ - inline UBool operator!= (const UnicodeString& text) const; + inline bool operator!= (const UnicodeString& text) const; /** * Greater than operator. Performs only bitwise comparison. @@ -1526,7 +1526,7 @@ public: */ virtual void extractBetween(int32_t start, int32_t limit, - UnicodeString& target) const; + UnicodeString& target) const override; /** * Copy the characters in the range @@ -1545,7 +1545,7 @@ public: * @param target the target buffer for extraction, can be NULL * if targetLength is 0 * @param targetCapacity the length of the target buffer - * @param inv Signature-distinguishing paramater, use US_INV. + * @param inv Signature-distinguishing parameter, use US_INV. * @return the output string length, not including the terminating NUL * @stable ICU 3.2 */ @@ -2456,14 +2456,14 @@ public: */ virtual void handleReplaceBetween(int32_t start, int32_t limit, - const UnicodeString& text); + const UnicodeString& text) override; /** * Replaceable API * @return true if it has MetaData * @stable ICU 2.4 */ - virtual UBool hasMetaData() const; + virtual UBool hasMetaData() const override; /** * Copy a substring of this object, retaining attribute (out-of-band) @@ -2478,7 +2478,7 @@ public: * dest >= limit`. * @stable ICU 2.0 */ - virtual void copy(int32_t start, int32_t limit, int32_t dest); + virtual void copy(int32_t start, int32_t limit, int32_t dest) override; /* Search and replace operations */ @@ -3274,7 +3274,7 @@ public: * \endcode * @param src String using only invariant characters. * @param textLength Length of src, or -1 if NUL-terminated. - * @param inv Signature-distinguishing paramater, use US_INV. + * @param inv Signature-distinguishing parameter, use US_INV. * * @see US_INV * @stable ICU 3.2 @@ -3338,7 +3338,7 @@ public: * @see getDynamicClassID * @stable ICU 2.6 */ - virtual UnicodeString *clone() const; + virtual UnicodeString *clone() const override; /** Destructor. * @stable ICU 2.0 @@ -3444,7 +3444,7 @@ public: * * @stable ICU 2.2 */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; //======================================== // Implementation methods @@ -3455,21 +3455,21 @@ protected: * Implement Replaceable::getLength() (see jitterbug 1027). * @stable ICU 2.4 */ - virtual int32_t getLength() const; + virtual int32_t getLength() const override; /** * The change in Replaceable to use virtual getCharAt() allows * UnicodeString::charAt() to be inline again (see jitterbug 709). * @stable ICU 2.4 */ - virtual char16_t getCharAt(int32_t offset) const; + virtual char16_t getCharAt(int32_t offset) const override; /** * The change in Replaceable to use virtual getChar32At() allows * UnicodeString::char32At() to be inline again (see jitterbug 709). * @stable ICU 2.4 */ - virtual UChar32 getChar32At(int32_t offset) const; + virtual UChar32 getChar32At(int32_t offset) const override; private: // For char* constructors. Could be made public. @@ -3946,7 +3946,7 @@ UnicodeString::doCompare(int32_t start, } } -inline UBool +inline bool UnicodeString::operator== (const UnicodeString& text) const { if(isBogus()) { @@ -3957,7 +3957,7 @@ UnicodeString::operator== (const UnicodeString& text) const } } -inline UBool +inline bool UnicodeString::operator!= (const UnicodeString& text) const { return (! operator==(text)); } diff --git a/thirdparty/icu4c/common/unicode/unorm.h b/thirdparty/icu4c/common/unicode/unorm.h index c3c57582d4..38fb895155 100644 --- a/thirdparty/icu4c/common/unicode/unorm.h +++ b/thirdparty/icu4c/common/unicode/unorm.h @@ -115,7 +115,7 @@ * unorm_normalize(UNORM_FCD) may be implemented with UNORM_NFD. * * For more details on FCD see the collation design document: - * http://source.icu-project.org/repos/icu/icuhtml/trunk/design/collation/ICU_collation_design.htm + * https://htmlpreview.github.io/?https://github.com/unicode-org/icu-docs/blob/main/design/collation/ICU_collation_design.htm * * ICU collation performs either NFD or FCD normalization automatically if normalization * is turned on for the collator object. diff --git a/thirdparty/icu4c/common/unicode/uobject.h b/thirdparty/icu4c/common/unicode/uobject.h index eeb331ce97..25a8330f9a 100644 --- a/thirdparty/icu4c/common/unicode/uobject.h +++ b/thirdparty/icu4c/common/unicode/uobject.h @@ -262,8 +262,8 @@ protected: // UObject &operator=(const UObject &other) { return *this; } // comparison operators - virtual inline UBool operator==(const UObject &other) const { return this==&other; } - inline UBool operator!=(const UObject &other) const { return !operator==(other); } + virtual inline bool operator==(const UObject &other) const { return this==&other; } + inline bool operator!=(const UObject &other) const { return !operator==(other); } // clone() commented out from the base class: // some compilers do not support co-variant return types diff --git a/thirdparty/icu4c/common/unicode/urename.h b/thirdparty/icu4c/common/unicode/urename.h index 737f4b308e..4605f632ea 100644 --- a/thirdparty/icu4c/common/unicode/urename.h +++ b/thirdparty/icu4c/common/unicode/urename.h @@ -58,6 +58,11 @@ /* C exports renaming data */ +#define CreateLSTMBreakEngine U_ICU_ENTRY_POINT_RENAME(CreateLSTMBreakEngine) +#define CreateLSTMData U_ICU_ENTRY_POINT_RENAME(CreateLSTMData) +#define CreateLSTMDataForScript U_ICU_ENTRY_POINT_RENAME(CreateLSTMDataForScript) +#define DeleteLSTMData U_ICU_ENTRY_POINT_RENAME(DeleteLSTMData) +#define LSTMDataName U_ICU_ENTRY_POINT_RENAME(LSTMDataName) #define T_CString_int64ToString U_ICU_ENTRY_POINT_RENAME(T_CString_int64ToString) #define T_CString_integerToString U_ICU_ENTRY_POINT_RENAME(T_CString_integerToString) #define T_CString_stringToInteger U_ICU_ENTRY_POINT_RENAME(T_CString_stringToInteger) @@ -381,6 +386,7 @@ #define u_strcmpFold U_ICU_ENTRY_POINT_RENAME(u_strcmpFold) #define u_strcpy U_ICU_ENTRY_POINT_RENAME(u_strcpy) #define u_strcspn U_ICU_ENTRY_POINT_RENAME(u_strcspn) +#define u_stringHasBinaryProperty U_ICU_ENTRY_POINT_RENAME(u_stringHasBinaryProperty) #define u_strlen U_ICU_ENTRY_POINT_RENAME(u_strlen) #define u_strncasecmp U_ICU_ENTRY_POINT_RENAME(u_strncasecmp) #define u_strncat U_ICU_ENTRY_POINT_RENAME(u_strncat) @@ -1575,6 +1581,7 @@ #define ures_countArrayItems U_ICU_ENTRY_POINT_RENAME(ures_countArrayItems) #define ures_findResource U_ICU_ENTRY_POINT_RENAME(ures_findResource) #define ures_findSubResource U_ICU_ENTRY_POINT_RENAME(ures_findSubResource) +#define ures_getAllChildrenWithFallback U_ICU_ENTRY_POINT_RENAME(ures_getAllChildrenWithFallback) #define ures_getAllItemsWithFallback U_ICU_ENTRY_POINT_RENAME(ures_getAllItemsWithFallback) #define ures_getBinary U_ICU_ENTRY_POINT_RENAME(ures_getBinary) #define ures_getByIndex U_ICU_ENTRY_POINT_RENAME(ures_getByIndex) @@ -1696,9 +1703,11 @@ #define uset_freeze U_ICU_ENTRY_POINT_RENAME(uset_freeze) #define uset_getItem U_ICU_ENTRY_POINT_RENAME(uset_getItem) #define uset_getItemCount U_ICU_ENTRY_POINT_RENAME(uset_getItemCount) +#define uset_getRangeCount U_ICU_ENTRY_POINT_RENAME(uset_getRangeCount) #define uset_getSerializedRange U_ICU_ENTRY_POINT_RENAME(uset_getSerializedRange) #define uset_getSerializedRangeCount U_ICU_ENTRY_POINT_RENAME(uset_getSerializedRangeCount) #define uset_getSerializedSet U_ICU_ENTRY_POINT_RENAME(uset_getSerializedSet) +#define uset_hasStrings U_ICU_ENTRY_POINT_RENAME(uset_hasStrings) #define uset_indexOf U_ICU_ENTRY_POINT_RENAME(uset_indexOf) #define uset_isEmpty U_ICU_ENTRY_POINT_RENAME(uset_isEmpty) #define uset_isFrozen U_ICU_ENTRY_POINT_RENAME(uset_isFrozen) diff --git a/thirdparty/icu4c/common/unicode/ures.h b/thirdparty/icu4c/common/unicode/ures.h index fff84043e8..a6c43f9537 100644 --- a/thirdparty/icu4c/common/unicode/ures.h +++ b/thirdparty/icu4c/common/unicode/ures.h @@ -44,9 +44,9 @@ * locale and then ask it for individual resources. * <P> * Resource bundles in ICU4C are currently defined using text files which conform to the following - * <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/bnf_rb.txt">BNF definition</a>. + * <a href="https://github.com/unicode-org/icu-docs/blob/main/design/bnf_rb.txt">BNF definition</a>. * More on resource bundle concepts and syntax can be found in the - * <a href="http://icu-project.org/userguide/ResourceManagement.html">Users Guide</a>. + * <a href="https://unicode-org.github.io/icu/userguide/locale/resources">Users Guide</a>. * <P> */ diff --git a/thirdparty/icu4c/common/unicode/uscript.h b/thirdparty/icu4c/common/unicode/uscript.h index 8448afda76..6cb1532808 100644 --- a/thirdparty/icu4c/common/unicode/uscript.h +++ b/thirdparty/icu4c/common/unicode/uscript.h @@ -484,6 +484,17 @@ typedef enum UScriptCode { /** @stable ICU 66 */ USCRIPT_YEZIDI = 192,/* Yezi */ + /** @stable ICU 70 */ + USCRIPT_CYPRO_MINOAN = 193,/* Cpmn */ + /** @stable ICU 70 */ + USCRIPT_OLD_UYGHUR = 194,/* Ougr */ + /** @stable ICU 70 */ + USCRIPT_TANGSA = 195,/* Tnsa */ + /** @stable ICU 70 */ + USCRIPT_TOTO = 196,/* Toto */ + /** @stable ICU 70 */ + USCRIPT_VITHKUQI = 197,/* Vith */ + #ifndef U_HIDE_DEPRECATED_API /** * One more than the highest normal UScriptCode value. @@ -491,7 +502,7 @@ typedef enum UScriptCode { * * @deprecated ICU 58 The numeric value may change over time, see ICU ticket #12420. */ - USCRIPT_CODE_LIMIT = 193 + USCRIPT_CODE_LIMIT = 198 #endif // U_HIDE_DEPRECATED_API } UScriptCode; diff --git a/thirdparty/icu4c/common/unicode/uset.h b/thirdparty/icu4c/common/unicode/uset.h index 1d0daf9d09..2ef352ef56 100644 --- a/thirdparty/icu4c/common/unicode/uset.h +++ b/thirdparty/icu4c/common/unicode/uset.h @@ -719,16 +719,21 @@ uset_retainAll(USet* set, const USet* retain); * possible space, without changing this object's value. * A frozen set will not be modified. * - * @param set the object on which to perfrom the compact + * @param set the object on which to perform the compact * @stable ICU 3.2 */ U_CAPI void U_EXPORT2 uset_compact(USet* set); /** - * Inverts this set. This operation modifies this set so that - * its value is its complement. This operation does not affect - * the multicharacter strings, if any. + * This is equivalent to + * <code>uset_complementRange(set, 0, 0x10FFFF)</code>. + * + * <strong>Note:</strong> This performs a symmetric difference with all code points + * <em>and thus retains all multicharacter strings</em>. + * In order to achieve a “code point complement” (all code points minus this set), + * the easiest is to <code>uset_complement(set); uset_removeAllStrings(set);</code>. + * * A frozen set will not be modified. * @param set the set * @stable ICU 2.4 @@ -851,6 +856,16 @@ uset_removeAllStrings(USet* set); U_CAPI UBool U_EXPORT2 uset_isEmpty(const USet* set); +#ifndef U_HIDE_DRAFT_API +/** + * @param set the set + * @return true if this set contains multi-character strings or the empty string. + * @draft ICU 70 + */ +U_CAPI UBool U_EXPORT2 +uset_hasStrings(const USet *set); +#endif // U_HIDE_DRAFT_API + /** * Returns true if the given USet contains the given character. * This function works faster with a frozen set. @@ -901,8 +916,13 @@ uset_indexOf(const USet* set, UChar32 c); /** * Returns the character at the given index within this set, where * the set is ordered by ascending code point. If the index is - * out of range, return (UChar32)-1. The inverse of this method is - * <code>indexOf()</code>. + * out of range for characters, returns (UChar32)-1. + * The inverse of this method is <code>indexOf()</code>. + * + * For iteration, this is slower than uset_getRangeCount()/uset_getItemCount() + * with uset_getItem(), because for each call it skips linearly over <code>index</code> + * characters in the ranges. + * * @param set the set * @param charIndex an index from 0..size()-1 to obtain the char for * @return the character at the given index, or (UChar32)-1. @@ -912,16 +932,34 @@ U_CAPI UChar32 U_EXPORT2 uset_charAt(const USet* set, int32_t charIndex); /** - * Returns the number of characters and strings contained in the given - * USet. + * Returns the number of characters and strings contained in this set. + * The last (uset_getItemCount() - uset_getRangeCount()) items are strings. + * + * This is slower than uset_getRangeCount() and uset_getItemCount() because + * it counts the code points of all ranges. + * * @param set the set * @return a non-negative integer counting the characters and strings * contained in set * @stable ICU 2.4 + * @see uset_getRangeCount */ U_CAPI int32_t U_EXPORT2 uset_size(const USet* set); +#ifndef U_HIDE_DRAFT_API +/** + * @param set the set + * @return the number of ranges in this set. + * @draft ICU 70 + * @see uset_getItemCount + * @see uset_getItem + * @see uset_size + */ +U_CAPI int32_t U_EXPORT2 +uset_getRangeCount(const USet *set); +#endif // U_HIDE_DRAFT_API + /** * Returns the number of items in this set. An item is either a range * of characters or a single multicharacter string. @@ -935,20 +973,30 @@ uset_getItemCount(const USet* set); /** * Returns an item of this set. An item is either a range of - * characters or a single multicharacter string. + * characters or a single multicharacter string (which can be the empty string). + * + * If <code>itemIndex</code> is less than uset_getRangeCount(), then this function returns 0, + * and the range is <code>*start</code>..<code>*end</code>. + * + * If <code>itemIndex</code> is at least uset_getRangeCount() and less than uset_getItemCount(), then + * this function copies the string into <code>str[strCapacity]</code> and + * returns the length of the string (0 for the empty string). + * + * If <code>itemIndex</code> is out of range, then this function returns -1. + * + * Note that 0 is returned for each range as well as for the empty string. + * * @param set the set - * @param itemIndex a non-negative integer in the range 0.. - * uset_getItemCount(set)-1 - * @param start pointer to variable to receive first character - * in range, inclusive - * @param end pointer to variable to receive last character in range, - * inclusive + * @param itemIndex a non-negative integer in the range 0..uset_getItemCount(set)-1 + * @param start pointer to variable to receive first character in range, inclusive; + * can be NULL for a string item + * @param end pointer to variable to receive last character in range, inclusive; + * can be NULL for a string item * @param str buffer to receive the string, may be NULL * @param strCapacity capacity of str, or 0 if str is NULL - * @param ec error code - * @return the length of the string (>= 2), or 0 if the item is a - * range, in which case it is the range *start..*end, or -1 if - * itemIndex is out of range + * @param ec error code; U_INDEX_OUTOFBOUNDS_ERROR if the itemIndex is out of range + * @return the length of the string (0 or >= 2), or 0 if the item is a range, + * or -1 if the itemIndex is out of range * @stable ICU 2.4 */ U_CAPI int32_t U_EXPORT2 diff --git a/thirdparty/icu4c/common/unicode/usetiter.h b/thirdparty/icu4c/common/unicode/usetiter.h index a817ef72b3..5834c308e4 100644 --- a/thirdparty/icu4c/common/unicode/usetiter.h +++ b/thirdparty/icu4c/common/unicode/usetiter.h @@ -33,9 +33,7 @@ class UnicodeString; * code points or ranges have been returned, it returns the * multicharacter strings of the UnicodeSet, if any. * - * This class is not intended to be subclassed. Consider any fields - * or methods declared as "protected" to be private. The use of - * protected in this class is an artifact of history. + * This class is not intended for public subclassing. * * <p>To iterate over code points and strings, use a loop like this: * <pre> @@ -60,25 +58,23 @@ class UnicodeString; * } * } * </pre> + * + * To iterate over only the strings, start with <code>skipToStrings()</code>. + * * @author M. Davis * @stable ICU 2.4 */ -class U_COMMON_API UnicodeSetIterator : public UObject { - - protected: - +class U_COMMON_API UnicodeSetIterator U_FINAL : public UObject { /** * Value of <tt>codepoint</tt> if the iterator points to a string. * If <tt>codepoint == IS_STRING</tt>, then examine * <tt>string</tt> for the current iteration result. - * @stable ICU 2.4 */ enum { IS_STRING = -1 }; /** * Current code point, or the special value <tt>IS_STRING</tt>, if * the iterator points to a string. - * @stable ICU 2.4 */ UChar32 codepoint; @@ -89,7 +85,6 @@ class U_COMMON_API UnicodeSetIterator : public UObject { * iterating over code points using <tt>next()</tt>, or if * <tt>codepoint == IS_STRING</tt>, then the value of * <tt>codepointEnd</tt> is undefined. - * @stable ICU 2.4 */ UChar32 codepointEnd; @@ -97,7 +92,6 @@ class U_COMMON_API UnicodeSetIterator : public UObject { * If <tt>codepoint == IS_STRING</tt>, then <tt>string</tt> points * to the current string. If <tt>codepoint != IS_STRING</tt>, the * value of <tt>string</tt> is undefined. - * @stable ICU 2.4 */ const UnicodeString* string; @@ -170,6 +164,25 @@ class U_COMMON_API UnicodeSetIterator : public UObject { */ const UnicodeString& getString(); +#ifndef U_HIDE_DRAFT_API + /** + * Skips over the remaining code points/ranges, if any. + * A following call to next() or nextRange() will yield a string, if there is one. + * No-op if next() would return false, or if it would yield a string anyway. + * + * @return *this + * @draft ICU 70 + * @see UnicodeSet#strings() + */ + inline UnicodeSetIterator &skipToStrings() { + // Finish code point/range iteration. + range = endRange; + endElement = -1; + nextElement = 0; + return *this; + } +#endif // U_HIDE_DRAFT_API + /** * Advances the iteration position to the next element in the set, * which can be either a single code point or a string. @@ -242,71 +255,58 @@ class U_COMMON_API UnicodeSetIterator : public UObject { * * @stable ICU 2.4 */ - virtual UClassID getDynamicClassID() const; + virtual UClassID getDynamicClassID() const override; // ======================= PRIVATES =========================== - protected: +private: // endElement and nextElements are really UChar32's, but we keep // them as signed int32_t's so we can do comparisons with // endElement set to -1. Leave them as int32_t's. /** The set - * @stable ICU 2.4 */ const UnicodeSet* set; /** End range - * @stable ICU 2.4 */ int32_t endRange; /** Range - * @stable ICU 2.4 */ int32_t range; /** End element - * @stable ICU 2.4 */ int32_t endElement; /** Next element - * @stable ICU 2.4 */ int32_t nextElement; - //UBool abbreviated; /** Next string - * @stable ICU 2.4 */ int32_t nextString; /** String count - * @stable ICU 2.4 */ int32_t stringCount; /** * Points to the string to use when the caller asks for a * string and the current iteration item is a code point, not a string. - * @internal */ UnicodeString *cpString; /** Copy constructor. Disallowed. - * @stable ICU 2.4 */ - UnicodeSetIterator(const UnicodeSetIterator&); // disallow + UnicodeSetIterator(const UnicodeSetIterator&) = delete; /** Assignment operator. Disallowed. - * @stable ICU 2.4 */ - UnicodeSetIterator& operator=(const UnicodeSetIterator&); // disallow + UnicodeSetIterator& operator=(const UnicodeSetIterator&) = delete; /** Load range - * @stable ICU 2.4 */ - virtual void loadRange(int32_t range); - + void loadRange(int32_t range); }; inline UBool UnicodeSetIterator::isString() const { - return codepoint == (UChar32)IS_STRING; + return codepoint < 0; } inline UChar32 UnicodeSetIterator::getCodepoint() const { diff --git a/thirdparty/icu4c/common/unicode/ustring.h b/thirdparty/icu4c/common/unicode/ustring.h index 10ea45ead1..5452fbe09a 100644 --- a/thirdparty/icu4c/common/unicode/ustring.h +++ b/thirdparty/icu4c/common/unicode/ustring.h @@ -72,7 +72,7 @@ * their occurrence is rare. Almost all characters in modern use require only * a single UChar code unit (i.e., their code point values are <=0xffff). * - * For more details see the User Guide Strings chapter (http://icu-project.org/userguide/strings.html). + * For more details see the User Guide Strings chapter (https://unicode-org.github.io/icu/userguide/strings/). * For a discussion of the handling of unpaired surrogates see also * Jitterbug 2145 and its icu mailing list proposal on 2002-sep-18. */ diff --git a/thirdparty/icu4c/common/unicode/utypes.h b/thirdparty/icu4c/common/unicode/utypes.h index 7c4ea7ac28..f890d5d1db 100644 --- a/thirdparty/icu4c/common/unicode/utypes.h +++ b/thirdparty/icu4c/common/unicode/utypes.h @@ -400,7 +400,7 @@ typedef double UDate; * suitable subclass. * * For more information, see: - * http://icu-project.org/userguide/conventions + * https://unicode-org.github.io/icu/userguide/dev/codingguidelines#details-about-icu-error-codes * * Note: By convention, ICU functions that take a reference (C++) or a pointer * (C) to a UErrorCode first test: @@ -479,16 +479,14 @@ typedef enum UErrorCode { U_COLLATOR_VERSION_MISMATCH = 28, /**< Collator version is not compatible with the base version */ U_USELESS_COLLATOR_ERROR = 29, /**< Collator is options only and no base is specified */ U_NO_WRITE_PERMISSION = 30, /**< Attempt to modify read-only or constant data. */ -#ifndef U_HIDE_DRAFT_API /** * The input is impractically long for an operation. * It is rejected because it may lead to problems such as excessive * processing time, stack depth, or heap memory requirements. * - * @draft ICU 68 + * @stable ICU 68 */ U_INPUT_TOO_LONG_ERROR = 31, -#endif // U_HIDE_DRAFT_API #ifndef U_HIDE_DEPRECATED_API /** diff --git a/thirdparty/icu4c/common/unicode/uvernum.h b/thirdparty/icu4c/common/unicode/uvernum.h index b09d4943c1..42e8865d7e 100644 --- a/thirdparty/icu4c/common/unicode/uvernum.h +++ b/thirdparty/icu4c/common/unicode/uvernum.h @@ -60,7 +60,7 @@ * This value will change in the subsequent releases of ICU * @stable ICU 2.4 */ -#define U_ICU_VERSION_MAJOR_NUM 69 +#define U_ICU_VERSION_MAJOR_NUM 70 /** The current ICU minor version as an integer. * This value will change in the subsequent releases of ICU @@ -86,7 +86,7 @@ * This value will change in the subsequent releases of ICU * @stable ICU 2.6 */ -#define U_ICU_VERSION_SUFFIX _69 +#define U_ICU_VERSION_SUFFIX _70 /** * \def U_DEF2_ICU_ENTRY_POINT_RENAME @@ -139,7 +139,7 @@ * This value will change in the subsequent releases of ICU * @stable ICU 2.4 */ -#define U_ICU_VERSION "69.1" +#define U_ICU_VERSION "70.1" /** * The current ICU library major version number as a string, for library name suffixes. @@ -152,13 +152,13 @@ * * @stable ICU 2.6 */ -#define U_ICU_VERSION_SHORT "69" +#define U_ICU_VERSION_SHORT "70" #ifndef U_HIDE_INTERNAL_API /** Data version in ICU4C. * @internal ICU 4.4 Internal Use Only **/ -#define U_ICU_DATA_VERSION "69.1" +#define U_ICU_DATA_VERSION "70.1" #endif /* U_HIDE_INTERNAL_API */ /*=========================================================================== |